© 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

    .start() method call (negative activations)

    python-code · gemini-2.5-flash-lite

    np.array constructor

    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
    date
    -0.06
     label
    -0.05
         
    -0.04
     continue
    -0.03
    ays
    -0.03
    [neighbor
    -0.03
    .y
    -0.03
    get
    -0.03
    neighbor
    -0.03
             
    -0.03
    Positive Logits
     it
    0.04
    itial
    0.04
    sen
    0.03
    umn
    0.02
    _to
    0.02
     k
    0.02
    put
    0.01
     target
    0.01
    for
    0.01
    list
    0.01
    Activations Density 93.171%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    while loop with index f (negative activations)

    python-code · gemini-2.5-flash-lite

    `random` module functions or comparisons

    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
    alse
    -0.05
    rue
    -0.05
    False
    -0.04
    True
    -0.04
     True
    -0.03
     False
    -0.03
     +=
    -0.03
    =True
    -0.02
    lse
    -0.02
     and
    -0.02
    Positive Logits
    _ch
    0.03
    ch
    0.03
     ch
    0.03
     char
    0.02
    .ch
    0.02
     [[
    0.02
     tuple
    0.02
     ("
    0.01
     [(
    0.01
    97
    0.01
    Activations Density 78.428%

    No Known Activations