© 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. 7530
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    digit after modulo 3 (negative activations)

    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
     +
    -0.06
    +
    -0.05
    ness
    -0.05
     +=
    -0.05
     function
    -0.04
     between
    -0.03
     algorithm
    -0.03
    work
    -0.03
    [(
    -0.03
     main
    -0.02
    POSITIVE LOGITS
     rows
    0.06
     <=
    0.05
     heapq
    0.05
    ...
    0.05
     col
    0.04
    _nodes
    0.04
    ound
    0.04
    queue
    0.04
     nodes
    0.04
    _queue
    0.04
    Activations Density 0.394%

    No Known Activations