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

    Neuronpedia

    INDEX
    Explanations

    replacing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     remarque
    0.47
     powied
    0.44
    ить
    0.43
     lửa
    0.42
    再说
    0.42
    เหลือ
    0.42
     вещи
    0.41
     தெரிவிக்க
    0.41
     parlano
    0.41
     छेड़
    0.41
    POSITIVE LOGITS
     replacing
    1.99
     replace
    1.96
     replaces
    1.92
    replace
    1.90
    Replace
    1.86
     Replace
    1.86
     Replacing
    1.82
     replacement
    1.80
    Replacing
    1.80
     replacements
    1.78
    Act Density 0.329%

    No Known Activations