© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5867
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    print function call (negative activations)

    python-code · gemini-2.5-flash-lite

    random.uniform and np. methods

    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
    ateg
    -0.04
    ool
    -0.04
    visited
    -0.04
    ess
    -0.03
    ree
    -0.03
    .parent
    -0.03
     visited
    -0.03
     rows
    -0.03
    isited
    -0.03
    POSITIVE LOGITS
     form
    0.06
    ction
    0.03
    ctor
    0.03
    ctions
    0.03
    cted
    0.03
    red
    0.03
    -
    0.03
    ility
    0.03
     en
    0.03
    ct
    0.03
    Activations Density 93.068%

    No Known Activations