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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3521
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    Python's itertools module

    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
     break
    -0.11
    97
    -0.07
    95
    -0.07
    98
    -0.07
    99
    -0.06
    city
    -0.06
    9
    -0.06
    90
    -0.05
    we
    -0.05
    100
    -0.04
    POSITIVE LOGITS
    etween
    0.12
    ĭ
    0.10
    oth
    0.08
    ip
    0.07
    duct
    0.06
    t
    0.06
    ts
    0.05
    section
    0.05
    ted
    0.05
     lon
    0.04
    Activations Density 27.964%

    No Known Activations