© 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

    exponentiation operator

    python-code · gemini-2.5-flash-lite

    comma separating list items (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
    gest
    -0.09
     {↵
    -0.08
    90
    -0.07
    ',↵
    -0.07
    ,↵
    -0.06
     {'
    -0.05
    essage
    -0.05
     {"
    -0.05
    ",↵
    -0.05
    25
    -0.05
    Positive Logits
    update
    0.07
    ork
    0.06
    (new
    0.06
     update
    0.06
    new
    0.06
     new
    0.06
    da
    0.05
    fe
    0.05
    old
    0.05
    lat
    0.05
    Activations Density 100.000%

    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