© 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 and arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    return statement followed by 'a'

    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
    .remove
    -0.02
    _i
    -0.01
    (i
    -0.01
    ool
    -0.01
     found
    -0.01
    loat
    -0.01
    [j
    -0.01
    .add
    -0.01
     j
    -0.01
     i
    -0.01
    Positive Logits
    ai
    0.05
    ome
    0.05
    am
    0.04
    a
    0.04
    _a
    0.03
    A
    0.03
     all
    0.03
    all
    0.03
     a
    0.03
    (a
    0.03
    Activations Density 38.032%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    beginning of a for loop (negative activations)

    python-code · gemini-2.5-flash-lite

    slicing expression

    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
    )↵↵↵
    -0.03
    ↵↵↵
    -0.02
    ove
    -0.02
     if
    -0.02
     dx
    -0.01
    +
    -0.01
     while
    -0.01
     If
    -0.01
     +
    -0.01
    <|
    -0.01
    Positive Logits
    dom
    0.02
    .split
    0.02
    split
    0.01
    .read
    0.01
    .strip
    0.01
    ":
    0.01
     var
    0.01
    strip
    0.01
     loc
    0.01
    ':
    0.01
    Activations Density 85.076%

    No Known Activations