© 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. 4678
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    not in 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
    anage
    -0.04
    (g
    -0.04
     heapq
    -0.03
     float
    -0.03
    :-
    -0.03
     str
    -0.03
    ilen
    -0.03
     ob
    -0.03
    t
    -0.03
    itude
    -0.03
    POSITIVE LOGITS
     set
    0.04
    En
    0.02
    he
    0.02
    ]),
    0.02
    ber
    0.02
     be
    0.02
    ho
    0.02
    °
    0.02
    _mo
    0.02
    ith
    0.02
    Activations Density 90.520%

    No Known Activations