© 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. 2285
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    'al' followed by 'ance' (negative activations)

    python-code · gemini-2.5-flash-lite

    number literals (digits)

    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
    uel
    -0.03
    _cost
    -0.03
    value
    -0.03
     lat
    -0.02
     cost
    -0.02
    rice
    -0.02
    riority
    -0.02
     val
    -0.02
     values
    -0.02
     value
    -0.02
    POSITIVE LOGITS
     sele
    0.02
    22
    0.02
     it
    0.01
    hi
    0.01
    py
    0.01
    }
    0.01
    ing
    0.01
     self
    0.00
    '
    0.00
    #
    0.00
    Activations Density 47.307%

    No Known Activations