© 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

    string literal assignment (negative activations)

    python-code · gemini-2.5-flash-lite

    string literal

    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
     it
    -0.06
    ,↵
    -0.04
    ,
    -0.03
    ][
    -0.03
    param
    -0.02
    args
    -0.02
     lat
    -0.02
    ',
    -0.01
     each
    -0.01
    arg
    -0.01
    Positive Logits
     :
    0.03
    _op
    0.03
    arest
    0.02
    :
    0.01
    <extra_output_id:2047>
    0.01
    ar
    0.01
     ↵
    0.01
     e
    0.01
    ak
    0.00
    un
    0.00
    Activations Density 99.973%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `in range` or `range` (negative activations)

    python-code · gemini-2.5-flash-lite

    list assignment

    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
     tuple
    -0.04
    .find
    -0.04
    .get
    -0.04
     get
    -0.04
     Tuple
    -0.04
     ("
    -0.04
    get
    -0.03
     Get
    -0.03
    101
    -0.03
     [(
    -0.03
    Positive Logits
    rint
    0.07
    hild
    0.04
    _neighbor
    0.04
     new
    0.04
    hildren
    0.03
    _ne
    0.03
    (new
    0.03
     next
    0.03
     Return
    0.03
     return
    0.03
    Activations Density 77.656%

    No Known Activations