© 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. 2-MLP
    11. 4561
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    self.attribute assignment (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
    Not in Any Lists

    No Comments

    Negative Logits
    if
    -0.07
    &
    -0.06
     di
    -0.05
    |
    -0.05
    *
    -0.05
    %
    -0.05
    !
    -0.05
    +
    -0.04
    /
    -0.04
    _dep
    -0.04
    POSITIVE LOGITS
     Testing
    0.19
     Test
    0.18
    print
    0.13
    de
    0.10
    les
    0.09
    ci
    0.08
    sert
    0.08
    ount
    0.07
     typing
    0.07
    stru
    0.06
    Activations Density 46.563%

    No Known Activations