© 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. 6-MLP
    11. 5253
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    exponentiation operator

    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
     sele
    -0.04
    ffe
    -0.03
     found
    -0.03
    ?
    -0.03
    imum
    -0.03
    iz
    -0.02
     it
    -0.02
    adjac
    -0.02
    hi
    -0.02
    py
    -0.02
    POSITIVE LOGITS
    =
    0.08
    1
    0.08
     a
    0.06
    ='
    0.06
    ="
    0.06
    uel
    0.06
     first
    0.05
     W
    0.05
    d
    0.05
    =True
    0.05
    Activations Density 3.971%

    No Known Activations