© 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

    tuple unpacking assignment

    python-code · gemini-2.5-flash-lite

    return statement (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
    rt
    -0.04
    rid
    -0.03
    ct
    -0.02
     Tuple
    -0.02
     dist
    -0.02
     distances
    -0.02
    os
    -0.02
    lay
    -0.02
     distance
    -0.01
    arg
    -0.01
    Positive Logits
     for
    0.02
    ,↵
    0.02
    ()
    0.01
     :
    0.01
    is
    0.01
    80
    0.01
    ef
    0.01
    de
    0.01
    le
    0.01
    <extra_output_id:2047>
    0.01
    Activations Density 98.976%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis of a function call

    python-code · gemini-2.5-flash-lite

    closing parenthesis of 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
    .split
    -0.06
     break
    -0.06
     function
    -0.06
     plt
    -0.05
     def
    -0.05
    split
    -0.05
    .read
    -0.05
    .strip
    -0.05
    (int
    -0.04
     between
    -0.04
    Positive Logits
    udoku
    0.06
     Create
    0.05
    itial
    0.04
     given
    0.04
    0
    0.04
    (N
    0.04
    anage
    0.04
    instance
    0.03
    [n
    0.03
    olver
    0.03
    Activations Density 99.056%

    No Known Activations