© 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 definition name 'a' (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
     Ex
    -0.03
     exp
    -0.02
    `
    -0.02
    _n
    -0.01
     ->
    -0.01
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Positive Logits
     enum
    0.04
    ateg
    0.04
    ¢
    0.04
    en
    0.03
    sen
    0.03
    ren
    0.03
    den
    0.03
    ven
    0.03
    ency
    0.03
    En
    0.03
    Activations Density 93.067%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    get★ho★stname or host attribute

    python-code · gemini-2.5-flash-lite

    list comprehension 'for ... in ...' (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
    _dep
    -0.01
     depth
    -0.01
     whe
    -0.01
     dep
    -0.01
    us
    -0.01
     step
    -0.01
    of
    -0.01
     pro
    -0.01
    is
    -0.01
    idth
    -0.01
    Positive Logits
    :-
    0.04
    (self
    0.03
    chedule
    0.03
    itude
    0.03
    ache
    0.03
    anage
    0.03
    loor
    0.03
    resh
    0.03
    reshold
    0.03
     self
    0.03
    Activations Density 100.000%

    No Known Activations