© 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. 7888
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list indexing and slicing (negative activations)

    python-code · gemini-2.5-flash-lite

    indexing with zero

    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
     each
    -0.04
     continue
    -0.03
     (
    -0.03
    fset
    -0.03
    }:
    -0.03
     [
    -0.03
    label
    -0.03
     label
    -0.03
     possible
    -0.02
    hor
    -0.02
    POSITIVE LOGITS
    [n
    0.04
     ny
    0.04
    ]][
    0.04
    hild
    0.04
     dfs
    0.04
    (n
    0.04
    _neighbor
    0.03
     new
    0.03
     nx
    0.03
     n
    0.03
    Activations Density 67.165%

    No Known Activations