© 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

    .hexdigest method call

    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
     W
    -0.05
    W
    -0.05
     H
    -0.04
    H
    -0.03
    rid
    -0.02
    reshold
    -0.02
    ange
    -0.02
    ar
    -0.02
     w
    -0.02
    ents
    -0.02
    Positive Logits
    _al
    0.03
    arch
    0.03
    tim
    0.03
    iz
    0.03
    lif
    0.02
    _op
    0.02
    as
    0.02
    _pro
    0.01
    _search
    0.01
    sp
    0.01
    Activations Density 43.091%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function argument or variable (negative activations)

    python-code · gemini-2.5-flash-lite

    csv reader followed by parenthesis

    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
    ('
    -0.06
     ("
    -0.06
    ("
    -0.06
     ['
    -0.06
     ["
    -0.06
    ['
    -0.05
    .e
    -0.04
    ="
    -0.04
    ["
    -0.04
    Positive Logits
    â
    0.04
     open
    0.04
    Â
    0.02
    stac
    0.02
    .index
    0.02
    (op
    0.02
    (int
    0.01
    ^
    0.01
    Ķ
    0.01
    _to
    0.01
    Activations Density 98.884%

    No Known Activations