© 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. 5507
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import 'xml.etree.ElementTree' as ET

    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
    ith
    -0.04
    _grid
    -0.03
     with
    -0.03
    The
    -0.03
    iven
    -0.03
    .heapp
    -0.03
     the
    -0.03
     The
    -0.03
    ri
    -0.02
    structions
    -0.02
    POSITIVE LOGITS
    loat
    0.04
    ithm
    0.03
    78
    0.03
    34
    0.03
    int
    0.03
    45
    0.03
     enum
    0.03
     pair
    0.03
    56
    0.02
    123
    0.02
    Activations Density 6.406%

    No Known Activations