© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3804
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    type checks with isinstance (negative activations)

    python-code · gemini-2.5-flash-lite

    numbers after array access

    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
     :
    -0.04
     ->
    -0.03
    ,
    -0.02
    sen
    -0.02
     contain
    -0.02
     =
    -0.01
     temp
    -0.01
     Calculate
    -0.01
    put
    -0.01
    =
    -0.01
    POSITIVE LOGITS
     _
    0.03
     [↵
    0.03
    e
    0.02
    ):↵
    0.02
    ce
    0.02
    get
    0.02
     e
    0.02
     get
    0.01
    ist
    0.01
    re
    0.01
    Activations Density 58.461%

    No Known Activations