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

    Neuronpedia

    INDEX
    Explanations

    purpose or action following prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     лучших
    0.48
     mendapatkan
    0.46
     nello
    0.43
    因为它
    0.42
     Iván
    0.42
     decirlo
    0.42
     uzys
    0.41
     በተ
    0.40
     Оно
    0.40
     스타일
    0.40
    POSITIVE LOGITS
     use
    0.66
     आपण
    0.53
     you
    0.52
    use
    0.50
     Use
    0.48
    用来
    0.46
     तुम्ही
    0.46
     você
    0.45
    Use
    0.45
    you
    0.45
    Act Density 0.183%

    No Known Activations