© 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

    closing bracket or brace (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
    udok
    -0.06
    lauses
    -0.05
    dom
    -0.05
     by
    -0.05
    _by
    -0.05
    udoku
    -0.05
    lause
    -0.04
    timal
    -0.04
    ]['
    -0.04
    straints
    -0.04
    Positive Logits
    _tree
    0.07
    quired
    0.05
    maining
    0.05
    _position
    0.05
    tier
    0.04
    _state
    0.04
    _population
    0.04
    ")<|
    0.04
    _move
    0.04
     """
    0.04
    Activations Density 98.119%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis for function call

    python-code · gemini-2.5-flash-lite

    string literal 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
    é
    -0.04
    æ
    -0.04
    å
    -0.04
    è
    -0.04
    ä
    -0.03
    ory
    -0.03
    hest
    -0.03
    ç
    -0.03
    are
    -0.03
    rent
    -0.03
    Positive Logits
    ats
    0.04
    age
    0.03
    at
    0.03
    ater
    0.02
    att
    0.02
    ati
    0.02
    ating
    0.02
    atch
    0.02
    inf
    0.02
    ata
    0.02
    Activations Density 100.000%

    No Known Activations