© 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. 2-MLP
    11. 5751
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    index `k-1` or `j-1`

    python-code · gemini-2.5-flash-lite

    if condition involving self or len (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
     Value
    -0.04
    opulation
    -0.04
    _per
    -0.04
     population
    -0.04
    -0.04
    _population
    -0.03
     [[
    -0.03
    _total
    -0.03
    -0.03
    -0.03
    POSITIVE LOGITS
    }:
    0.06
    ):↵
    0.06
    )
    0.05
    (),
    0.05
    (self
    0.04
     representing
    0.04
    ']
    0.04
    ail
    0.03
    ])
    0.03
    weight
    0.03
    Activations Density 100.000%

    No Known Activations