© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5022
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class definition (negative activations)

    python-code · gemini-2.5-flash-lite

    accessing object attribute .x

    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
    er
    -0.02
     not
    -0.02
    _valid
    -0.02
    No
    -0.02
     pass
    -0.02
     valid
    -0.02
    uple
    -0.02
    _pos
    -0.01
    uples
    -0.01
     !=
    -0.01
    POSITIVE LOGITS
    _rate
    0.02
    _li
    0.02
    utation
    0.02
    apac
    0.01
    rack
    0.01
    temp
    0.01
    _matrix
    0.01
    _capacity
    0.01
    vai
    0.01
    apacity
    0.01
    Activations Density 90.943%

    No Known Activations