© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5471
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list comprehension for loop (negative activations)

    python-code · gemini-2.5-flash-lite

    'k' in 'tkinter as tk' or 'for a', 'def a'

    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
     function
    -0.02
    -0.01
    -0.01
     of
    -0.00
    _str
    -0.00
    _string
    -0.00
     from
    -0.00
    _list
    -0.00
    raw
    -0.00
     target
    -0.00
    POSITIVE LOGITS
    0.04
            ↵
    0.02
    0.02
    0.01
     and
    0.01
    -
    0.01
     -
    0.01
    ,
    0.01
    s
    0.00
    _end
    0.00
    Activations Density 99.532%

    No Known Activations