© 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. 4750
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable names and literals (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
     closest
    -0.13
    (point
    -0.11
    age
    -0.11
     distance
    -0.10
    _distance
    -0.10
     distances
    -0.10
     point
    -0.09
    _distances
    -0.09
    oint
    -0.09
    _point
    -0.08
    POSITIVE LOGITS
    p
    0.13
    [start
    0.11
    start
    0.10
    etwork
    0.09
    irst
    0.09
    (start
    0.09
    rect
    0.09
    .edges
    0.09
    raph
    0.08
    _start
    0.08
    Activations Density 98.694%

    No Known Activations