© 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. 6275
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable name `b` (negative activations)

    python-code · gemini-2.5-flash-lite

    condition followed by colon

    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
     raise
    -0.09
     return
    -0.08
     Returns
    -0.08
     Return
    -0.08
     break
    -0.07
    None
    -0.07
    alse
    -0.06
     not
    -0.06
     !=
    -0.05
     []↵↵
    -0.05
    POSITIVE LOGITS
     Calculate
    0.04
    alculate
    0.03
    alc
    0.03
     calculate
    0.03
    },
    0.02
    valu
    0.02
     distances
    0.02
     &
    0.02
     if
    0.02
    ],
    0.02
    Activations Density 100.000%

    No Known Activations