© 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. 7812
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import hashlib

    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
    N
    -0.06
     N
    -0.04
    ution
    -0.04
     to
    -0.04
     lon
    -0.03
    l
    -0.03
    i
    -0.03
    lit
    -0.03
    ld
    -0.03
     L
    -0.03
    POSITIVE LOGITS
    ag
    0.06
    me
    0.05
    hor
    0.05
    ig
    0.04
    ame
    0.04
    gment
    0.04
     This
    0.04
    gle
    0.03
    age
    0.03
    m
    0.03
    Activations Density 25.735%

    No Known Activations