© 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 arguments

    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
     search
    -0.05
    ][
    -0.04
     *
    -0.04
    _search
    -0.04
    reshold
    -0.04
    *
    -0.04
    .append
    -0.03
     model
    -0.03
    [(
    -0.03
    isi
    -0.03
    Positive Logits
    type
    0.06
     typ
    0.05
     <=
    0.05
    ype
    0.05
    ub
    0.05
    lable
    0.05
    yp
    0.05
    I
    0.05
     G
    0.05
    [v
    0.04
    Activations Density 6.742%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to variable `f`

    python-code · gemini-2.5-flash-lite

    assignment or augmented 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
    ["
    -0.04
    ['
    -0.04
     representing
    -0.03
    .keys
    -0.03
    .split
    -0.02
     between
    -0.02
     heuristic
    -0.02
    .values
    -0.02
    .items
    -0.02
    _route
    -0.02
    Positive Logits
    ron
    0.05
     heap
    0.05
     heapq
    0.05
    .pop
    0.04
     while
    0.03
     second
    0.03
    queue
    0.03
    left
    0.03
    orted
    0.03
    erge
    0.03
    Activations Density 80.690%

    No Known Activations