© 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

    function definition start (negative activations)

    python-code · gemini-2.5-flash-lite

    elif or else keyword

    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
    ',
    -0.04
    :
    -0.04
    ",
    -0.04
    ;
    -0.03
    .strip
    -0.03
    ~
    -0.03
    ","
    -0.03
    :↵
    -0.02
    ,
    -0.02
     ",
    -0.02
    Positive Logits
    {
    0.02
    re
    0.01
    (neighbor
    0.01
    ck
    0.01
    dividual
    0.01
    es
    0.01
    (input
    0.01
     whi
    0.01
    _index
    0.00
     index
    0.00
    Activations Density 53.688%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    delete dictionary items

    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
     while
    -0.06
    .append
    -0.02
    ode
    -0.02
     -=
    -0.02
    .remove
    -0.02
    .add
    -0.02
     +=
    -0.02
     total
    -0.01
     If
    -0.01
    .write
    -0.01
    Positive Logits
     graph
    0.03
    .name
    0.02
    .id
    0.02
     Get
    0.02
     grid
    0.02
    uple
    0.02
    _idx
    0.02
    or
    0.02
    dex
    0.02
    (map
    0.02
    Activations Density 63.053%

    No Known Activations