© 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. 7270
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    isinstance checks

    python-code · gemini-2.5-flash-lite

    `.delete` method (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
    ket
    -0.11
    la
    -0.10
    gest
    -0.10
    essage
    -0.09
    ec
    -0.09
    split
    -0.09
    pected
    -0.08
    ta
    -0.08
    el
    -0.08
    airs
    -0.08
    POSITIVE LOGITS
     random
    0.10
    .random
    0.10
    random
    0.08
    0.07
    [s
    0.05
    (s
    0.05
    lat
    0.05
    9
    0.05
    .randint
    0.04
    ype
    0.04
    Activations Density 100.000%

    No Known Activations