© 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. 6493
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment `c = d` (negative activations)

    python-code · gemini-2.5-flash-lite

    index of a list element

    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
     plt
    -0.07
    len
    -0.03
    idth
    -0.03
     len
    -0.03
    _len
    -0.03
     size
    -0.03
    otal
    -0.03
    -
    -0.02
    _length
    -0.02
     length
    -0.02
    POSITIVE LOGITS
     not
    0.09
    No
    0.08
    [n
    0.06
    lse
    0.05
     and
    0.05
    lif
    0.05
     !=
    0.05
     if
    0.05
    Error
    0.05
     elif
    0.04
    Activations Density 100.000%

    No Known Activations