© 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

    the `__name__ == '__main__'` check (negative activations)

    python-code · gemini-2.5-flash-lite

    multiplication by 6 or 25

    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
     Calculate
    -0.05
    alculate
    -0.04
    alc
    -0.04
    prese
    -0.04
     calculate
    -0.04
    valu
    -0.03
    _scores
    -0.02
     float
    -0.02
     comp
    -0.02
     sorted
    -0.01
    Positive Logits
     *
    0.03
    *
    0.03
    .ch
    0.02
     **
    0.02
     //
    0.02
     index
    0.02
    _index
    0.02
     ==
    0.01
     root
    0.01
    **
    0.01
    Activations Density 48.174%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    len of list slicing (negative activations)

    python-code · gemini-2.5-flash-lite

    print function arguments

    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
    fset
    -0.09
     by
    -0.06
    _by
    -0.06
    ort
    -0.05
     while
    -0.05
    ilename
    -0.05
    reshold
    -0.05
     possible
    -0.05
    hor
    -0.05
    _file
    -0.05
    Positive Logits
     form
    0.05
    alculate
    0.04
    inal
    0.04
    Ł
    0.04
    result
    0.03
     results
    0.03
     total
    0.03
     result
    0.03
    _result
    0.03
    isi
    0.03
    Activations Density 94.880%

    No Known Activations