Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enum
    -0.08
    .gradient
    -0.08
    	fclose
    -0.07
    annels
    -0.07
    ojis
    -0.07
     Toy
    -0.07
    adores
    -0.07
    /address
    -0.07
    ующие
    -0.07
     meantime
    -0.07
    POSITIVE LOGITS
    采购
    0.06
     aer
    0.06
    �始化
    0.06
     fatalError
    0.06
     violates
    0.05
     гід
    0.05
     parish
    0.05
    “The
    0.05
     викон
    0.05
    kın
    0.05
    Act Density 0.013%

    No Known Activations