© 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. 5855
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment or definition

    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
    :
    -0.06
    :",
    -0.06
     :
    -0.06
    :-
    -0.05
     ->
    -0.05
     -
    -0.04
    ]['
    -0.04
    /
    -0.04
    [-
    -0.03
     raise
    -0.03
    POSITIVE LOGITS
    timal
    0.07
    losest
    0.05
     optimal
    0.04
     best
    0.04
     closest
    0.03
    gest
    0.03
    arest
    0.03
     shortest
    0.03
    hortest
    0.03
    erge
    0.03
    Activations Density 36.298%

    No Known Activations