© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 7904
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    for loops or for comprehension (negative activations)

    python-code · gemini-2.5-flash-lite

    checking for divisibility by 2

    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
     next
    -0.02
    _with
    -0.01
     nx
    -0.01
    _al
    -0.01
    ith
    -0.01
    arch
    -0.01
    ab
    -0.01
    tim
    -0.01
     whe
    -0.01
     pi
    -0.01
    POSITIVE LOGITS
     !=
    0.05
    (range
    0.04
     else
    0.03
     elif
    0.03
     for
    0.01
    Ł
    0.01
     },↵
    0.01
    :-
    0.01
    ameters
    0.01
     break
    0.01
    Activations Density 98.361%

    No Known Activations