© 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. 6-MLP
    11. 6006
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random function calls (negative activations)

    python-code · gemini-2.5-flash-lite

    if statement condition

    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
    uel
    -0.05
     values
    -0.05
    _cost
    -0.04
    value
    -0.04
     lat
    -0.04
     cost
    -0.04
    rice
    -0.04
    £
    -0.03
    riority
    -0.03
     val
    -0.03
    POSITIVE LOGITS
    xF
    0.08
     us
    0.06
     between
    0.05
     based
    0.05
     on
    0.04
     it
    0.04
     by
    0.04
     that
    0.04
    _from
    0.04
    _by
    0.04
    Activations Density 99.333%

    No Known Activations