© 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. 7650
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    lambda function arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    numbers in floating point literals

    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
    reshold
    -0.04
     iter
    -0.03
    ateg
    -0.03
     steps
    -0.03
     while
    -0.02
    _step
    -0.02
     step
    -0.02
     run
    -0.02
    und
    -0.02
     population
    -0.02
    POSITIVE LOGITS
     |
    0.02
     lon
    0.02
    _sum
    0.02
     parent
    0.02
    [start
    0.01
    ge
    0.01
    J
    0.01
    Ħ
    0.01
    Z
    0.01
    lat
    0.01
    Activations Density 90.248%

    No Known Activations