© 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

    colon before indented block

    python-code · gemini-2.5-flash-lite

    closing parenthesis of a function call (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
    v
    -0.07
    verage
    -0.07
     heuristic
    -0.06
    vent
    -0.06
     visited
    -0.05
    gre
    -0.05
    (w
    -0.04
    cies
    -0.04
    ot
    -0.04
    cy
    -0.04
    Positive Logits
    ")↵
    0.09
    ")↵↵
    0.09
    }")↵
    0.09
    ')↵
    0.09
    pected
    0.08
    ')↵↵
    0.08
    <extra_output_id:2047>
    0.08
    }")↵↵
    0.08
    ")<|
    0.07
    "↵↵
    0.07
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable array assignment (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
    xF
    -0.08
    ?
    -0.06
    loat
    -0.05
    ype
    -0.05
    sp
    -0.04
    our
    -0.04
    K
    -0.04
     (
    -0.03
    .random
    -0.03
     y
    -0.03
    Positive Logits
    ({
    0.08
    e
    0.07
    ('
    0.07
    ("
    0.07
    ([
    0.07
    erson
    0.07
    (),
    0.06
    (self
    0.06
    ((
    0.06
    ())
    0.06
    Activations Density 18.018%

    No Known Activations