© 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. 7692
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    is None checks

    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
     dp
    -0.05
     =
    -0.04
    _comb
    -0.03
     adj
    -0.03
    adj
    -0.03
    _counts
    -0.03
     possible
    -0.03
     that
    -0.03
     comb
    -0.02
    _sum
    -0.02
    POSITIVE LOGITS
     None
    0.08
     True
    0.06
     False
    0.06
    ener
    0.06
     range
    0.06
     '__
    0.04
    als
    0.04
     ValueError
    0.04
     "__
    0.04
    ample
    0.04
    Activations Density 51.843%

    No Known Activations