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

    Neuronpedia

    INDEX
    Explanations

    preposition 'at'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    里面
    0.69
    上面
    0.65
    入れ
    0.65
     মধ্যে
    0.64
     মধ্যেও
    0.64
    当中
    0.63
    пи
    0.62
    裡面
    0.61
     විසින්
    0.60
    সর
    0.59
    POSITIVE LOGITS
     at
    4.09
     At
    3.06
    At
    2.95
     atthe
    2.69
     tại
    2.66
    at
    2.48
     atth
    1.98
    @
    1.85
     AT
    1.82
     atleast
    1.74
    Act Density 0.761%

    No Known Activations