© 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

    attribute access (`.`) or key access (`[]`) (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
    distances
    -0.13
     closest
    -0.12
    dist
    -0.12
    umn
    -0.12
     distance
    -0.12
    arest
    -0.12
    _distance
    -0.12
    ordinates
    -0.11
    rite
    -0.11
    _distances
    -0.11
    Positive Logits
     dp
    0.22
    _counts
    0.17
     Testing
    0.16
     test
    0.16
     Test
    0.15
    _comb
    0.14
    test
    0.12
     possible
    0.11
     comb
    0.10
    _sum
    0.10
    Activations Density 99.985%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    elif keyword

    python-code · gemini-2.5-flash-lite

    origin or figure followed by '(' (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
    ]][
    -0.07
    .read
    -0.07
    ates
    -0.07
     dp
    -0.06
    ry
    -0.06
    ree
    -0.05
    h
    -0.05
               
    -0.05
    ating
    -0.04
    ool
    -0.04
    Positive Logits
     continue
    0.13
    =None
    0.07
     None
    0.07
     two
    0.07
     main
    0.06
     dict
    0.06
     break
    0.06
    air
    0.06
     population
    0.05
    sions
    0.05
    Activations Density 100.000%

    No Known Activations