© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 6106
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    f in list comprehension (negative activations)

    python-code · gemini-2.5-flash-lite

    variable access or method call `.get()`

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Not in Any Lists

    No Comments

    Negative Logits
    append
    -0.07
    .append
    -0.06
    .strip
    -0.05
    [int
    -0.04
    .txt
    -0.04
     []↵↵
    -0.04
     []↵
    -0.04
    loat
    -0.04
    lse
    -0.03
    (int
    -0.03
    POSITIVE LOGITS
    .is
    0.05
    ].
    0.05
    .num
    0.05
    .in
    0.04
     file
    0.03
    ..
    0.03
     Di
    0.02
    .remove
    0.02
     assign
    0.02
     word
    0.02
    Activations Density 72.824%

    No Known Activations