© 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. 6-MLP
    11. 2457
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list indexing and slicing (negative activations)

    python-code · gemini-2.5-flash-lite

    variable assigned in 'with open' block

    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
    [neighbor
    -0.05
    hildren
    -0.05
    neighbor
    -0.05
    hild
    -0.05
    next
    -0.05
     neighbor
    -0.04
     continue
    -0.04
    .append
    -0.04
     other
    -0.04
    ][
    -0.04
    POSITIVE LOGITS
    ab
    0.01
    list
    0.01
     not
    0.01
    valid
    0.01
    (node
    0.01
    sible
    0.01
     is
    0.01
     shortest
    0.01
    (n
    0.01
    .split
    0.01
    Activations Density 99.992%

    No Known Activations