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

    Neuronpedia

    INDEX
    Explanations

    action verbs with direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jedoch
    0.39
     በሚ
    0.39
     Ancak
    0.38
     በመ
    0.37
     特許
    0.36
     требу
    0.35
     মাতৃ
    0.35
     Необходимо
    0.35
     উত্প
    0.35
    鸴
    0.35
    POSITIVE LOGITS
     out
    0.73
     down
    0.68
     up
    0.65
     OUT
    0.61
     into
    0.60
     DOWN
    0.60
     outta
    0.60
     off
    0.59
     back
    0.59
     around
    0.53
    Act Density 0.038%

    No Known Activations