© 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. 3641
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assigning a list to 'array' (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
    },
    -0.07
     if
    -0.06
    l
    -0.06
    ],
    -0.06
     None
    -0.05
    e
    -0.05
    ],↵
    -0.05
    erson
    -0.05
     distances
    -0.03
    r
    -0.03
    POSITIVE LOGITS
     break
    0.23
     while
    0.11
     +=
    0.11
     th
    0.09
     continue
    0.07
     >
    0.06
    split
    0.06
    cond
    0.06
    lit
    0.05
    strip
    0.04
    Activations Density 57.179%

    No Known Activations