© 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

    incrementing by 1 (negative activations)

    python-code · gemini-2.5-flash-lite

    file opening as variable

    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
     range
    -0.03
     while
    -0.03
    _range
    -0.02
    ange
    -0.02
    range
    -0.02
    (range
    -0.02
    args
    -0.01
     enumerate
    -0.01
    ode
    -0.01
    ..
    -0.01
    Positive Logits
     co
    0.02
     graph
    0.01
     st
    0.01
     S
    0.01
     grid
    0.01
    or
    0.01
     represent
    0.01
    l
    0.01
     population
    0.01
     matrix
    0.01
    Activations Density 21.704%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `if` condition checks (negative activations)

    python-code · gemini-2.5-flash-lite

    return followed by boolean expression

    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
     not
    -0.07
    No
    -0.06
     !=
    -0.04
    Error
    -0.04
     no
    -0.03
     Tuple
    -0.03
    ry
    -0.03
    ()
    -0.02
     out
    -0.02
     al
    -0.02
    Positive Logits
     dfs
    0.04
    gorithm
    0.03
     algorithm
    0.03
    .index
    0.03
    jkstra
    0.03
     process
    0.02
     bre
    0.02
    ","
    0.02
     Find
    0.02
     search
    0.02
    Activations Density 72.080%

    No Known Activations