© 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

    exception variable after `as`

    python-code · gemini-2.5-flash-lite

    closing parenthesis (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
     for
    -0.05
    for
    -0.05
    lambda
    -0.03
    ):
    -0.03
     dp
    -0.02
    (point
    -0.02
    ")↵
    -0.01
    ")↵↵
    -0.01
    }")↵
    -0.01
    ')↵
    -0.01
    Positive Logits
    *
    0.02
     *
    0.02
    .pop
    0.02
    -
    0.02
     -
    0.02
    >
    0.01
    &
    0.01
    _end
    0.01
     <=
    0.01
    random
    0.01
    Activations Density 97.581%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method name letters and parenthesis

    python-code · gemini-2.5-flash-lite

    bracketed index 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
    input
    -0.04
    .txt
    -0.04
     model
    -0.04
    odel
    -0.03
     input
    -0.03
    _input
    -0.03
    stance
    -0.03
    (input
    -0.03
    ample
    -0.02
    straint
    -0.02
    Positive Logits
     _
    0.04
    .write
    0.02
     in
    0.02
    .is
    0.02
    .num
    0.01
     found
    0.01
     ==
    0.01
    .in
    0.01
    _conne
    0.01
     file
    0.01
    Activations Density 74.764%

    No Known Activations