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

    Neuronpedia

    INDEX
    Explanations

    turning to face

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بيك
    0.44
    隙
    0.41
    োধী
    0.39
    जव
    0.38
     planks
    0.38
    ệm
    0.38
    নমেন্ট
    0.37
     setIs
    0.36
    ìm
    0.36
    ések
    0.36
    POSITIVE LOGITS
     facing
    0.67
    facing
    0.64
    面向
    0.61
     faced
    0.59
    面对
    0.59
     Facing
    0.57
    面對
    0.56
    Facing
    0.56
    面临
    0.53
     abruptly
    0.48
    Act Density 0.006%

    No Known Activations