© 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. 4928
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    part of 'any' or 'animals'

    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
    ain
    -0.05
     main
    -0.04
    _t
    -0.04
    ut
    -0.04
    main
    -0.04
     us
    -0.04
     between
    -0.03
     tuple
    -0.03
     it
    -0.03
    _table
    -0.03
    POSITIVE LOGITS
    y
    0.07
    x
    0.04
    ount
    0.04
    temp
    0.04
    place
    0.04
     ex
    0.04
     variables
    0.03
    ual
    0.03
    tic
    0.03
     le
    0.03
    Activations Density 39.164%

    No Known Activations