© 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. 3531
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    equality comparison operator

    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
    type
    -0.07
     typ
    -0.06
    ype
    -0.06
    lable
    -0.06
    yp
    -0.06
    =
    -0.06
    =True
    -0.06
    ="
    -0.05
    _type
    -0.05
    ='
    -0.05
    POSITIVE LOGITS
     {}↵↵
    0.03
     found
    0.03
     {}↵
    0.03
    ?
    0.03
     []↵↵
    0.02
     collections
    0.02
     []↵
    0.02
     c
    0.02
    _c
    0.02
    cle
    0.02
    Activations Density 19.756%

    No Known Activations