© 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

    sys.exit()

    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
    (se
    -0.05
    .index
    -0.03
    n
    -0.02
    str
    -0.02
    adjac
    -0.02
    uccess
    -0.02
    _re
    -0.01
     conne
    -0.01
    duct
    -0.01
    ag
    -0.01
    Positive Logits
    it
    0.09
    _t
    0.09
    ination
    0.07
     t
    0.07
    .t
    0.07
    I
    0.06
    )↵↵↵
    0.06
    if
    0.06
    .e
    0.05
    inations
    0.05
    Activations Density 17.621%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function argument list (negative activations)

    python-code · gemini-2.5-flash-lite

    is followed by empty or prime

    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
     continue
    -0.04
     each
    -0.04
    _rate
    -0.03
    _input
    -0.03
     Get
    -0.03
    }:
    -0.03
     input
    -0.02
    _li
    -0.02
    utation
    -0.02
    .name
    -0.02
    Positive Logits
     found
    0.06
    isited
    0.05
     valid
    0.03
    _valid
    0.03
    over
    0.03
    orted
    0.03
    maining
    0.03
    visited
    0.03
    quired
    0.03
    use
    0.02
    Activations Density 50.762%

    No Known Activations