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

    Neuronpedia

    INDEX
    Explanations

    multiplication and other math operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     params
    0.78
    パラメータ
    0.77
     geochemistry
    0.75
    參數
    0.74
     parameterized
    0.73
     предотвра
    0.72
    idazol
    0.72
    lestage
    0.72
     passivation
    0.72
    謨
    0.72
    POSITIVE LOGITS
    Subtract
    1.35
     subtraction
    1.32
     Subtract
    1.29
     subtract
    1.25
     multiplication
    1.25
     Addition
    1.23
    subtract
    1.15
    Subtraction
    1.15
    Addition
    1.15
    Multiply
    1.14
    Act Density 0.510%

    No Known Activations