© 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
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. MLP
    5. 6-MLP
    6. 5034
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment or augmentation (negative activations)

    python-code · gemini-2.5-flash-lite

    'a' followed by ':' or 'def'

    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
    ness
    -0.05
     True
    -0.04
     ]↵
    -0.04
     def
    -0.04
     {'
    -0.04
     {"
    -0.04
    None
    -0.03
    |
    -0.03
     """↵
    -0.03
    POSITIVE LOGITS
    inal
    0.05
    result
    0.05
    mmon
    0.05
    hortest
    0.04
    timal
    0.04
    losest
    0.04
     result
    0.04
    _result
    0.04
     optimal
    0.03
     results
    0.03
    Activations Density 99.902%

    No Known Activations