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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2247
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random number generation

    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
    maining
    -0.07
    xtend
    -0.06
    prese
    -0.06
    ctionary
    -0.06
    dividual
    -0.06
    arest
    -0.05
    dices
    -0.05
    quest
    -0.05
    turn
    -0.05
    stance
    -0.05
    POSITIVE LOGITS
    ates
    0.04
    ation
    0.03
    atus
    0.03
    ating
    0.03
    ata
    0.02
    ate
    0.02
    G
    0.02
     G
    0.02
    inf
    0.02
    (G
    0.02
    Activations Density 12.583%

    No Known Activations