© 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. 2136
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    multiplication operation in expressions (negative activations)

    python-code · gemini-2.5-flash-lite

    exponentiation `** 2`

    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
    07
    -0.03
    01
    -0.03
    03
    -0.03
    00
    -0.03
    02
    -0.03
    0
    -0.03
    >
    -0.03
    05
    -0.02
    .n
    -0.02
     n
    -0.02
    POSITIVE LOGITS
     Calculate
    0.02
    atus
    0.02
    etween
    0.02
     abs
    0.01
    ta
    0.01
     math
    0.01
    ative
    0.01
     },↵
    0.01
    gle
    0.01
     ]↵
    0.01
    Activations Density 99.505%

    No Known Activations