© 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. 2-MLP
    11. 4924
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    create method call

    python-code · gemini-2.5-flash-lite

    lambda function arguments (negative activations)

    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
    reshold
    -0.08
    en
    -0.08
    udok
    -0.06
    ange
    -0.06
    rom
    -0.06
    .random
    -0.05
    ents
    -0.05
     we
    -0.05
    ency
    -0.05
    dom
    -0.05
    POSITIVE LOGITS
    (list
    0.06
    (in
    0.05
     base
    0.05
     t
    0.05
    ry
    0.05
    pected
    0.05
    graph
    0.05
     list
    0.04
    list
    0.04
    List
    0.04
    Activations Density 100.000%

    No Known Activations