© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 6590
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    _ne suffix

    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
    red
    -0.07
    per
    -0.07
     ny
    -0.05
    y
    -0.05
    isited
    -0.05
    or
    -0.05
     dy
    -0.05
    Y
    -0.04
     per
    -0.04
     as
    -0.04
    POSITIVE LOGITS
    arent
    0.07
     import
    0.06
     parent
    0.05
    (w
    0.05
    at
    0.04
    ise
    0.04
    ±
    0.04
     w
    0.04
    _w
    0.04
    .w
    0.03
    Activations Density 45.485%

    No Known Activations