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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.76
    h
    0.75
    ร้าย
    0.75
    y
    0.71
    s
    0.71
    a
    0.69
    g
    0.68
    usak
    0.67
    t
    0.67
    b
    0.67
    POSITIVE LOGITS
     withd
    0.94
    +
    0.92
     AgNO
    0.87
    '=
    0.86
    =\
    0.86
     गुणनखंड
    0.86
    }=
    0.85
    )}=
    0.85
     pued
    0.84
    }=-
    0.81
    Act Density 0.132%

    No Known Activations