© 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

    Python dictionary keys and values (negative activations)

    python-code · gemini-2.5-flash-lite

    methods ending with _data

    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
    .num
    -0.03
    idth
    -0.03
    .position
    -0.03
    _len
    -0.03
     tuple
    -0.03
    len
    -0.02
     size
    -0.02
    _size
    -0.02
     len
    -0.02
    size
    -0.02
    Positive Logits
    term
    0.02
    zero
    0.02
    over
    0.02
     char
    0.02
    jkstra
    0.02
    ~
    0.01
    =True
    0.01
     representing
    0.01
    umn
    0.01
    inal
    0.01
    Activations Density 34.937%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list index or literal number (negative activations)

    python-code · gemini-2.5-flash-lite

    string literal in loops or conditionals

    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
     import
    -0.04
    .split
    -0.04
    split
    -0.03
    .read
    -0.03
    .strip
    -0.03
    ('
    -0.02
    ['
    -0.02
    strip
    -0.02
    ("
    -0.02
    ["
    -0.02
    Positive Logits
    '.
    0.02
    @
    0.02
    {
    0.02
    .p
    0.01
    min
    0.01
    .txt
    0.01
     &
    0.01
     ad
    0.01
     for
    0.01
    _
    0.00
    Activations Density 100.000%

    No Known Activations