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

    Neuronpedia

    INDEX
    Explanations

    conditional statements involving you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可以让
    0.50
    Give
    0.49
     consequatur
    0.45
    人們
    0.44
    会让
    0.42
     فائدہ
    0.41
     대부분
    0.40
    我們可以
    0.39
    ხ
    0.39
    ประโยชน์
    0.38
    POSITIVE LOGITS
     está
    0.46
     got
    0.45
     fries
    0.45
     проходит
    0.44
     sedang
    0.43
    hangi
    0.43
     suffered
    0.43
     $=
    0.42
     née
    0.42
     geçir
    0.42
    Act Density 0.002%

    No Known Activations