© 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. 5419
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    is prefix for methods

    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
    ↵
    -0.04
     len
    -0.03
    ram
    -0.01
    -0.01
    -0.01
    -0.01
    cle
    -0.01
    -0.01
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    ate
    0.02
    ates
    0.02
    ated
    0.02
    Į
    0.02
    ating
    0.02
    ategory
    0.02
    ation
    0.02
    ator
    0.02
    ations
    0.02
    atri
    0.01
    Activations Density 37.413%

    No Known Activations