© 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. 4848
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    _index or index attribute/method

    python-code · gemini-2.5-flash-lite

    math module functions and attributes (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
    _un
    -0.07
    _move
    -0.07
    cess
    -0.06
     directions
    -0.06
     direction
    -0.06
    ut
    -0.06
    direction
    -0.06
    unction
    -0.05
     obstac
    -0.05
    un
    -0.05
    POSITIVE LOGITS
    yp
    0.07
     dictionary
    0.06
    dict
    0.06
    ctionary
    0.06
    keys
    0.05
     dict
    0.05
    apping
    0.05
    ({
    0.05
    £
    0.04
    _dict
    0.04
    Activations Density 100.000%

    No Known Activations