© 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

    modulo operator with length

    python-code · gemini-2.5-flash-lite

    opening parenthesis before argument (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
    None
    -0.03
    alse
    -0.03
     None
    -0.03
     []↵↵
    -0.03
     False
    -0.02
     []↵
    -0.02
     raise
    -0.02
     {}↵↵
    -0.02
     ValueError
    -0.02
    False
    -0.02
    Positive Logits
     and
    0.02
     &
    0.01
     based
    0.01
     [↵
    0.01
    _r
    0.00
     are
    0.00
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 91.306%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    literal string 'str'

    python-code · gemini-2.5-flash-lite

    assignment or attribute access (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
     out
    -0.01
    du
    -0.01
     order
    -0.01
     pre
    -0.01
     [(
    -0.01
     Y
    -0.01
     second
    -0.01
    or
    -0.01
    ri
    -0.01
    u
    -0.00
    Positive Logits
    .keys
    0.04
    ()↵
    0.02
    78
    0.02
    34
    0.02
    45
    0.02
    56
    0.02
    123
    0.02
    op
    0.01
    23
    0.01
     is
    0.01
    Activations Density 40.399%

    No Known Activations