© 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 calls and indexing (negative activations)

    python-code · gemini-2.5-flash-lite

    json.dumps and json.dump

    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
     !=
    -0.09
    gs
    -0.04
    ()<|
    -0.03
    ():↵
    -0.03
    ())
    -0.02
    ()
    -0.02
    ()↵↵
    -0.02
    ()↵
    -0.02
    ())↵
    -0.02
    (),
    -0.02
    Positive Logits
    ab
    0.03
     pi
    0.03
    lat
    0.02
    itude
    0.02
     lat
    0.02
    ge
    0.02
    .is
    0.02
     },↵
    0.01
    .num
    0.01
    text
    0.01
    Activations Density 97.872%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    parse or partition function calls

    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
    101
    -0.02
    atus
    -0.02
    ost
    -0.01
     return
    -0.01
     conne
    -0.01
    _for
    -0.01
    <|
    -0.01
    200
    -0.01
    hi
    -0.01
     spe
    -0.01
    Positive Logits
     parse
    0.05
    par
    0.03
    gre
    0.03
    light
    0.03
    25
    0.02
    (N
    0.02
    loat
    0.02
    .strip
    0.02
    qrt
    0.02
    .split
    0.02
    Activations Density 49.979%

    No Known Activations