© 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. 5571
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    from datetime import

    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
    .
    -0.03
    ¿
    -0.03
    _
    -0.03
    ess
    -0.03
    (
    -0.02
    vailable
    -0.02
    om
    -0.02
    _to
    -0.02
    dom
    -0.02
    POSITIVE LOGITS
    ue
    0.06
    ance
    0.04
    ant
    0.03
    ays
    0.03
    cted
    0.03
    .y
    0.03
    ct
    0.03
    date
    0.03
    ction
    0.03
    ctor
    0.03
    Activations Density 54.040%

    No Known Activations