© 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

    while loop condition

    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
    on
    -0.06
    ble
    -0.04
    ink
    -0.03
    one
    -0.03
    str
    -0.02
     visited
    -0.02
    £
    -0.02
    il
    -0.02
    qu
    -0.01
    Ľ
    -0.01
    Positive Logits
    an
    0.04
     e
    0.03
     us
    0.03
     between
    0.03
     based
    0.02
     on
    0.02
     by
    0.02
     that
    0.02
    _from
    0.02
    _by
    0.02
    Activations Density 44.274%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    tuple assignment with zero

    python-code · gemini-2.5-flash-lite

    `if __name__ ==` (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
     it
    -0.12
     each
    -0.03
    ver
    -0.02
     a
    -0.01
    _num
    -0.01
     (
    -0.01
    -0.01
     S
    -0.01
     i
    -0.01
     V
    -0.01
    Positive Logits
    atus
    0.05
     :
    0.04
    :-
    0.04
    itude
    0.04
    ache
    0.03
    dict
    0.03
    anage
    0.03
    loor
    0.03
    resh
    0.03
    reshold
    0.03
    Activations Density 99.866%

    No Known Activations