© 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. 2963
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `.append(` or `print(` (negative activations)

    python-code · gemini-2.5-flash-lite

    list index 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
    print
    -0.03
     print
    -0.02
    .pop
    -0.01
     E
    -0.01
    _part
    -0.01
    _str
    -0.01
     st
    -0.01
     |
    -0.00
    +
    -0.00
    '
    0.00
    POSITIVE LOGITS
    No
    0.06
    ner
    0.05
     n
    0.05
    .n
    0.04
    ':
    0.04
    ':↵
    0.04
     nx
    0.04
    (N
    0.04
    ":↵
    0.04
    num
    0.04
    Activations Density 70.513%

    No Known Activations