© 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. 4800
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random.random method call (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
    º
    -0.21
    _g
    -0.21
    ory
    -0.19
    hest
    -0.19
     gen
    -0.18
    .g
    -0.18
    _cities
    -0.18
    (g
    -0.17
    g
    -0.16
    gy
    -0.16
    POSITIVE LOGITS
    (maze
    0.18
     cell
    0.18
    (grid
    0.18
    _cell
    0.18
     cel
    0.18
    _cells
    0.18
    grid
    0.18
    [row
    0.17
    _grid
    0.17
    .grid
    0.16
    Activations Density 99.995%

    No Known Activations