© 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. 4584
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    parenthesis and list symbols (negative activations)

    python-code · gemini-2.5-flash-lite

    first parameter of a method

    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
     range
    -0.05
    ,↵
    -0.03
    ',↵
    -0.03
     },↵
    -0.03
     bo
    -0.03
     [↵
    -0.02
     """↵
    -0.02
    ",↵
    -0.02
    th
    -0.02
    },↵
    -0.02
    POSITIVE LOGITS
    alculate
    0.05
     calculate
    0.03
     total
    0.03
    ((
    0.03
    er
    0.03
    alc
    0.02
     break
    0.02
     pass
    0.02
    [:
    0.02
    total
    0.02
    Activations Density 96.013%

    No Known Activations