© 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. 2-MLP
    11. 7921
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    del keyword deleting from dictionary or list

    python-code · gemini-2.5-flash-lite

    list elements (negative activations)

    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
    quen
    -0.05
    il
    -0.05
    lable
    -0.05
    gree
    -0.04
    s
    -0.04
     enumerate
    -0.04
    rior
    -0.04
    quest
    -0.04
    t
    -0.04
    gist
    -0.04
    POSITIVE LOGITS
     direction
    0.04
     M
    0.03
    direction
    0.03
     P
    0.03
     Graph
    0.03
     Re
    0.03
     defaultdict
    0.03
     W
    0.03
     V
    0.03
     St
    0.03
    Activations Density 100.000%

    No Known Activations