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

    Neuronpedia

    INDEX
    Explanations

    the word down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    div
    0.44
     Rahmen
    0.40
     المقسوم
    0.40
    ขึ้น
    0.39
     boven
    0.39
     Dividing
    0.39
    0.38
     डिवाइड
    0.38
     расчет
    0.38
    پوینت
    0.38
    POSITIVE LOGITS
     down
    0.80
    下来
    0.70
     Down
    0.69
    down
    0.68
     DOWN
    0.68
     다운
    0.67
    DOWN
    0.66
     вниз
    0.66
    Down
    0.65
     डाउन
    0.64
    Act Density 0.034%

    No Known Activations