© 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. 5249
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment or structural element (negative activations)

    python-code · gemini-2.5-flash-lite

    list elements or numbers

    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
     \
    -0.03
     None
    -0.03
    None
    -0.03
    alse
    -0.01
    ise
    -0.01
     []↵↵
    -0.01
     False
    -0.01
     []↵
    -0.01
     raise
    -0.01
     {}↵↵
    -0.01
    POSITIVE LOGITS
    reshold
    0.05
    itude
    0.04
    vai
    0.04
    uel
    0.04
    endoftext
    0.04
    _scores
    0.03
     },↵
    0.03
    vailable
    0.03
    cles
    0.03
    dividual
    0.02
    Activations Density 99.733%

    No Known Activations