© 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. 2-MLP
    11. 5693
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    importing modules

    python-code · gemini-2.5-flash-lite

    assigning keyword arguments (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
    ump
    -0.10
     enumerate
    -0.09
    ack
    -0.09
    mpty
    -0.09
    mory
    -0.09
    otal
    -0.09
    valid
    -0.09
    gram
    -0.08
    ep
    -0.08
     instruction
    -0.08
    POSITIVE LOGITS
    itude
    0.06
     lat
    0.05
     score
    0.05
    _scores
    0.05
    cores
    0.05
    _score
    0.05
    his
    0.04
    core
    0.04
    .values
    0.04
     optimal
    0.04
    Activations Density 100.000%

    No Known Activations