© 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 or <= keyword following def (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
     re
    -0.05
     continue
    -0.04
     we
    -0.04
     exp
    -0.04
     tra
    -0.03
     per
    -0.03
    ...
    -0.03
     en
    -0.03
    _id
    -0.02
     break
    -0.02
    Positive Logits
    ].
    0.03
    e
    0.02
    erson
    0.02
     as
    0.02
    tex
    0.01
    tity
    0.01
     n
    0.01
    cel
    0.01
                                    
    0.01
    gle
    0.01
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    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
     ver
    -0.10
    _idx
    -0.09
    el
    -0.09
    (self
    -0.09
    ver
    -0.09
    hor
    -0.08
    ments
    -0.08
    Ě
    -0.07
    's
    -0.07
    self
    -0.07
    Positive Logits
     dictionary
    0.18
    dict
    0.17
     dict
    0.15
    .values
    0.13
     bre
    0.13
    ctionary
    0.12
    .keys
    0.12
    .items
    0.11
    Z
    0.11
    keys
    0.10
    Activations Density 54.956%

    No Known Activations