© 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

    `finally` or `flush`

    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
     ele
    -0.04
    str
    -0.04
    lat
    -0.03
    itude
    -0.03
    st
    -0.03
     lat
    -0.03
    um
    -0.03
    ab
    -0.02
    gor
    -0.02
    stru
    -0.02
    Positive Logits
    anage
    0.07
    olver
    0.06
    is
    0.06
    ush
    0.05
    append
    0.05
    an
    0.05
    uil
    0.04
     e
    0.04
    re
    0.04
    ator
    0.04
    Activations Density 70.053%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary key followed by colon

    python-code · gemini-2.5-flash-lite

    the `__name__` special variable (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
     defaultdict
    -0.04
    ([
    -0.04
     {}↵
    -0.04
    apping
    -0.04
     {}↵↵
    -0.04
    ctionary
    -0.02
    None
    -0.02
     float
    -0.02
     dict
    -0.02
    .add
    -0.02
    Positive Logits
    .split
    0.03
    name
    0.02
     name
    0.02
    ilename
    0.02
    .name
    0.02
    _name
    0.02
    .id
    0.02
    (len
    0.02
    is
    0.02
    len
    0.02
    Activations Density 74.868%

    No Known Activations