© 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. 2-MLP
    11. 7939
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    queue operations

    python-code · gemini-2.5-flash-lite

    conditional statements (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
    ates
    -0.10
    pected
    -0.08
    ating
    -0.07
    term
    -0.07
    ax
    -0.06
     base
    -0.05
    an
    -0.05
    ation
    -0.05
    ate
    -0.05
    zero
    -0.04
    POSITIVE LOGITS
    gest
    0.08
    maining
    0.08
    .m
    0.07
    quired
    0.06
    ry
    0.06
    á
    0.05
    (current
    0.05
    Æ
    0.05
    essage
    0.05
    [current
    0.05
    Activations Density 100.000%

    No Known Activations