© 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

    print followed by parenthesis (negative activations)

    python-code · gemini-2.5-flash-lite

    csv.writer or csv.DictReader

    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
     result
    -0.06
     results
    -0.04
     dp
    -0.04
     best
    -0.03
     elif
    -0.02
     output
    -0.02
     else
    -0.02
     solution
    -0.02
    .add
    -0.02
     total
    -0.02
    Positive Logits
    ith
    0.03
    ","
    0.02
    None
    0.02
    ",
    0.02
     with
    0.02
    ',
    0.02
    alse
    0.02
     None
    0.02
     []↵↵
    0.02
     spe
    0.02
    Activations Density 98.695%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literal `str` (negative activations)

    python-code · gemini-2.5-flash-lite

    comma followed by space or 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
    .find
    -0.03
     find
    -0.02
     Find
    -0.02
    ind
    -0.02
    atus
    -0.02
     found
    -0.02
    turn
    -0.02
    22
    -0.02
    vious
    -0.01
    arch
    -0.01
    Positive Logits
     graph
    0.05
    oard
    0.05
    aze
    0.05
    blem
    0.05
    grid
    0.04
    _grid
    0.04
     grid
    0.04
    udoku
    0.04
     maze
    0.04
    .grid
    0.04
    Activations Density 99.997%

    No Known Activations