© 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

    this is

    python-code · gemini-2.5-flash-lite

    closing dictionary brace (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
    ments
    -0.09
    red
    -0.07
    itness
    -0.07
    random
    -0.07
     best
    -0.07
    .random
    -0.06
    ted
    -0.06
     random
    -0.06
    opulation
    -0.05
    ment
    -0.05
    Positive Logits
     end
    0.06
    [s
    0.06
    [start
    0.05
    graph
    0.05
     s
    0.05
    cep
    0.05
    .keys
    0.05
    _s
    0.04
    _i
    0.04
    ["
    0.04
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    modulo operator

    python-code · gemini-2.5-flash-lite

    import statement keyword (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
    ;
    -0.06
    ulate
    -0.06
    ]][
    -0.06
    ulation
    -0.05
    >
    -0.05
    &
    -0.05
    <
    -0.05
    ch
    -0.05
    ul
    -0.05
    timal
    -0.05
    Positive Logits
    _i
    0.07
    h
    0.05
    ð
    0.04
    print
    0.04
    x
    0.04
     score
    0.04
    ad
    0.04
    _scores
    0.04
    cores
    0.04
    _score
    0.03
    Activations Density 100.000%

    No Known Activations