© 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

    opening file strings

    python-code · gemini-2.5-flash-lite

    attribute assignment `.` (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
    qrt
    -0.03
    [j
    -0.02
     abs
    -0.02
    ab
    -0.02
    .e
    -0.01
     elif
    -0.01
     as
    -0.01
     if
    -0.01
    .t
    -0.01
     del
    -0.01
    Positive Logits
     the
    0.04
     each
    0.03
    *
    0.02
     *
    0.02
    ique
    0.02
    &
    0.01
     whe
    0.01
     <=
    0.01
    _path
    0.01
     all
    0.01
    Activations Density 25.005%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    integer or string methods

    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
    .strip
    -0.09
     Create
    -0.08
    itial
    -0.07
    stance
    -0.06
     Initialize
    -0.06
     defaultdict
    -0.05
    ized
    -0.05
     [[
    -0.04
    network
    -0.04
    _graph
    -0.04
    Positive Logits
    gest
    0.08
    ice
    0.06
    i
    0.05
    gre
    0.05
    right
    0.05
    ¿
    0.04
    ise
    0.04
    l
    0.04
    re
    0.04
    ł
    0.04
    Activations Density 33.124%

    No Known Activations