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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5621
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .reader or .dictreader

    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
    .read
    -0.04
    .strip
    -0.03
    None
    -0.03
    strip
    -0.03
    alse
    -0.02
    .split
    -0.02
     None
    -0.02
    split
    -0.02
     []↵↵
    -0.02
     False
    -0.02
    POSITIVE LOGITS
    (re
    0.05
     re
    0.04
     Re
    0.04
    _re
    0.04
    .re
    0.04
    rect
    0.03
    re
    0.03
     remaining
    0.02
    ren
    0.02
    (len
    0.02
    Activations Density 76.859%

    No Known Activations