© 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. 5801
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment

    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
     None
    -0.09
     False
    -0.08
     []↵↵
    -0.06
    None
    -0.06
    alse
    -0.05
     []↵
    -0.04
     raise
    -0.04
    ("
    -0.04
     {}↵↵
    -0.04
     ValueError
    -0.04
    POSITIVE LOGITS
    join
    0.07
     (
    0.03
    rom
    0.03
     Par
    0.03
    ;
    0.02
    li
    0.02
     Def
    0.02
     given
    0.02
    ):↵
    0.02
     y
    0.02
    Activations Density 95.899%

    No Known Activations