© 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. 6336
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary key-value pairs (negative activations)

    python-code · gemini-2.5-flash-lite

    attributes like `max_workers` or `max_charge`

    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
    timal
    -0.08
    losest
    -0.08
     optimal
    -0.07
     best
    -0.07
     closest
    -0.06
    gest
    -0.06
    arest
    -0.06
     shortest
    -0.06
    hortest
    -0.06
    verage
    -0.05
    POSITIVE LOGITS
     all
    0.03
    all
    0.03
     any
    0.02
     the
    0.02
    ats
    0.02
    _part
    0.02
    at
    0.02
     function
    0.02
    _str
    0.02
     me
    0.01
    Activations Density 9.984%

    No Known Activations