© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 3177
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    ascii characters or asyncio

    python-code · gemini-2.5-flash-lite

    return True (negative activations)

    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
    Negative Logits
    ast
    -0.08
    14
    -0.07
    75
    -0.06
    arg
    -0.05
    5
    -0.05
     Returns
    -0.04
    T
    -0.04
    0
    -0.04
     E
    -0.04
    25
    -0.03
    POSITIVE LOGITS
    endoftext
    0.07
    ative
    0.06
    itude
    0.06
    ion
    0.06
    ance
    0.06
    ied
    0.05
    ren
    0.05
    utes
    0.05
    istic
    0.05
    alue
    0.05
    Activations Density 100.000%

    No Known Activations