© 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

    float division and modulo operations (negative activations)

    python-code · gemini-2.5-flash-lite

    `year` or `median`

    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
    et
    -0.02
    rite
    -0.02
     E
    -0.01
    name
    -0.01
    ath
    -0.01
    rc
    -0.01
     ny
    -0.01
    ype
    -0.01
    type
    -0.01
    fig
    -0.01
    Positive Logits
    e
    0.05
    ce
    0.04
     e
    0.03
    ist
    0.03
    re
    0.03
    reate
    0.01
    inal
    0.01
    result
    0.01
     re
    0.01
     result
    0.01
    Activations Density 75.706%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    most_common (negative activations)

    python-code · gemini-2.5-flash-lite

    `strftime` method calls

    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
    alculate
    -0.03
    enerate
    -0.02
     calculate
    -0.02
     find
    -0.02
     parse
    -0.02
     generate
    -0.02
     create
    -0.02
     Calculate
    -0.02
    ulate
    -0.02
     Find
    -0.02
    Positive Logits
     elif
    0.02
     else
    0.02
    Ł
    0.01
     },↵
    0.01
    :-
    0.01
     &
    0.01
    ta
    0.01
     comb
    0.01
     ad
    0.01
     x
    0.00
    Activations Density 61.516%

    No Known Activations