© 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. 2-MLP
    11. 5563
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    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
    index
    -0.07
    n
    -0.07
    u
    -0.07
    p
    -0.07
    c
    -0.07
    t
    -0.06
    int
    -0.06
    j
    -0.06
    con
    -0.05
    row
    -0.05
    POSITIVE LOGITS
     continue
    0.08
    .ran
    0.07
    .randint
    0.06
    _shortest
    0.05
    .random
    0.05
    .edges
    0.04
     Output
    0.04
    s
    0.03
    tem
    0.03
    arch
    0.03
    Activations Density 2.675%

    No Known Activations