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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location, time, or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     如果
    0.24
     bitOp
    0.23
     অথবা
    0.23
     hMut
    0.22
    ステル
    0.22
     表示
    0.22
     አንዳንድ
    0.22
     словарь
    0.22
     způ
    0.21
     లేదా
    0.21
    POSITIVE LOGITS
    і
    0.24
     both
    0.24
    -
    0.21
    and
    0.20
     this
    0.20
     that
    0.19
    и
    0.19
    ها
    0.19
    ذ
    0.19
    сле
    0.19
    Act Density 0.350%

    No Known Activations