© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `is_empty()` or `.insert()` method calls

    python-code · gemini-2.5-flash-lite

    route definition parameters (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    _distance
    -0.16
     distance
    -0.16
    _distances
    -0.15
    distance
    -0.15
     closest
    -0.15
    _coordinates
    -0.14
     distances
    -0.14
    distances
    -0.13
    arest
    -0.13
    losest
    -0.13
    Positive Logits
     moves
    0.21
    direction
    0.20
     move
    0.18
     directions
    0.18
     direction
    0.17
    turn
    0.17
    mmand
    0.17
     instructions
    0.16
    _move
    0.16
     steps
    0.15
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    return statements

    python-code · gemini-2.5-flash-lite

    colon followed by newline or if (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ted
    -0.05
    ound
    -0.05
    ard
    -0.05
    dition
    -0.04
    .graph
    -0.04
    id
    -0.04
    ed
    -0.04
    uzz
    -0.04
    index
    -0.04
    n
    -0.04
    Positive Logits
    cep
    0.10
    gle
    0.08
    ili
    0.07
    action
    0.07
     action
    0.07
    hicle
    0.07
    ility
    0.07
    ket
    0.06
    ilities
    0.06
    ron
    0.06
    Activations Density 100.000%

    No Known Activations