© 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. 5833
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    special method names

    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
     heapq
    -0.05
    e
    -0.04
    queue
    -0.04
    _queue
    -0.04
    dd
    -0.04
     -
    -0.03
    ce
    -0.03
    re
    -0.03
    riority
    -0.03
     heap
    -0.03
    POSITIVE LOGITS
    <extra_output_id:2047>
    0.08
    uple
    0.05
    [(
    0.05
     left
    0.04
     temp
    0.03
     _
    0.03
     ↵
    0.03
    left
    0.03
    times
    0.03
    (map
    0.03
    Activations Density 71.044%

    No Known Activations