© 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

    or operator in conditionals

    python-code · gemini-2.5-flash-lite

    push or flush method (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
                           
    -0.11
    ates
    -0.08
    č
    -0.07
    ='
    -0.07
                               
    -0.07
    reshold
    -0.06
    ="
    -0.06
    (r
    -0.05
    ange
    -0.05
    ents
    -0.04
    Positive Logits
    class
    0.08
    uccess
    0.07
    own
    0.06
    apac
    0.06
    ateg
    0.06
    arent
    0.06
    otal
    0.06
    l
    0.06
    code
    0.06
    ruck
    0.05
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment with equals (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
     not
    -0.05
     raise
    -0.05
     <=
    -0.04
     new
    -0.03
    ak
    -0.02
    .keys
    -0.02
    [-
    -0.02
     or
    -0.01
    ()↵
    -0.01
    .f
    -0.01
    Positive Logits
     ==
    0.19
    param
    0.14
    args
    0.13
    arg
    0.09
     Par
    0.09
     par
    0.08
    _par
    0.08
    =
    0.07
    par
    0.07
    ames
    0.05
    Activations Density 24.674%

    No Known Activations