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

    Neuronpedia

    INDEX
    Explanations

    increment operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reception
    0.67
    죄
    0.63
    Long
    0.62
    Eas
    0.60
    ร้าย
    0.59
    My
    0.59
    Vict
    0.59
    :
    0.58
    Never
    0.58
    Minus
    0.57
    POSITIVE LOGITS
     ++
    2.29
     incremento
    1.95
     Increment
    1.89
     increment
    1.88
     (++
    1.84
     증가
    1.79
     ++;
    1.78
    ++
    1.75
    ++,
    1.75
    Increment
    1.70
    Act Density 0.156%

    No Known Activations