© 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

    is_prime or is_empty checks

    python-code · gemini-2.5-flash-lite

    sorted() call (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
    .write
    -0.05
     print
    -0.04
    print
    -0.04
    (re
    -0.04
     function
    -0.04
    ilename
    -0.03
    _file
    -0.03
    ilen
    -0.03
     me
    -0.03
     file
    -0.03
    Positive Logits
    '.
    0.04
    >
    0.03
    alse
    0.03
    rue
    0.03
    False
    0.02
    quence
    0.02
    True
    0.02
    quen
    0.02
    als
    0.02
    ample
    0.02
    Activations Density 42.422%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary key strings

    python-code · gemini-2.5-flash-lite

    attribute access (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
     dfs
    -0.04
     elif
    -0.03
    gorithm
    -0.03
     algorithm
    -0.03
    jkstra
    -0.03
     else
    -0.03
     bre
    -0.03
     continue
    -0.03
     Find
    -0.02
     search
    -0.02
    Positive Logits
     #
    0.02
    (len
    0.02
    <extra_output_id:2047>
    0.02
    #
    0.02
     for
    0.02
     not
    0.02
     """↵
    0.02
    \
    0.01
     |
    0.01
     return
    0.01
    Activations Density 100.000%

    No Known Activations