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

    Neuronpedia

    INDEX
    Explanations

    assigning into, to, onto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    且
    0.53
    の場合は
    0.50
    Obj
    0.49
    されない
    0.49
    ociaż
    0.49
    แต่
    0.48
    എം
    0.48
    Mismatch
    0.48
    Puzzle
    0.47
    はもちろん
    0.46
    POSITIVE LOGITS
     into
    1.78
     onto
    1.48
     إلى
    1.39
    into
    1.27
     Into
    1.23
     kepada
    1.20
     to
    1.19
     vào
    1.09
     الى
    1.09
     naar
    1.06
    Act Density 0.032%

    No Known Activations