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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     юк
    0.38
    TRR
    0.38
    '";
    0.37
    ন্ম
    0.36
    nego
    0.36
     yêu
    0.36
     contraste
    0.36
     অস্তিত্ব
    0.35
     kapcs
    0.35
    χή
    0.34
    POSITIVE LOGITS
     direction
    2.72
    方向
    2.58
    direction
    2.45
     방향
    2.44
    Direction
    2.42
     Direction
    2.41
     направление
    2.27
    的方向
    2.22
     DIRECTION
    2.20
     方向
    2.20
    Act Density 0.064%

    No Known Activations