© 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. 2243
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    html tag h1

    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
     while
    -0.08
    ch
    -0.07
     iter
    -0.05
    udoku
    -0.05
    (s
    -0.04
    >
    -0.03
     steps
    -0.02
    (he
    -0.02
    (i
    -0.02
    aze
    -0.02
    POSITIVE LOGITS
    h
    0.15
     ny
    0.06
    y
    0.05
     dy
    0.05
    ad
    0.05
    Y
    0.05
    .txt
    0.04
     Y
    0.04
    ver
    0.04
    igh
    0.04
    Activations Density 25.719%

    No Known Activations