© 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. 5547
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    range arguments

    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
    .index
    -0.04
    isited
    -0.04
    =True
    -0.04
    .strip
    -0.03
    tity
    -0.02
    orted
    -0.02
    maining
    -0.02
    visited
    -0.02
    quired
    -0.02
    use
    -0.02
    POSITIVE LOGITS
    66
    0.04
    ep
    0.03
    26
    0.01
    vertices
    0.01
    blem
    0.01
    15
    0.01
    form
    0.01
    42
    0.01
    44
    0.01
    Ń
    0.01
    Activations Density 9.273%

    No Known Activations