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

    Neuronpedia

    INDEX
    Explanations

    broad, square face

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imperfections
    0.38
    Gesture
    0.38
     gestures
    0.38
    ROBERT
    0.37
    抨
    0.35
    螂
    0.34
    Pract
    0.34
     мав
    0.34
     snar
    0.34
     conservatism
    0.34
    POSITIVE LOGITS
     圆
    0.43
     fists
    0.43
     лицо
    0.41
     chubby
    0.41
    ဴ
    0.41
     oily
    0.41
     redonde
    0.41
    합니다
    0.40
    圆
    0.40
     합니다
    0.40
    Act Density 0.000%

    No Known Activations