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

    Neuronpedia

    INDEX
    Explanations

    your/yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     제가
    0.61
     deras
    0.59
     leurs
    0.57
     themselves
    0.53
    เพิ่มเติม
    0.51
     خواهند
    0.50
     їх
    0.49
     ہماری
    0.49
     their
    0.48
     તેમના
    0.48
    POSITIVE LOGITS
     yourself
    1.16
    yourself
    0.96
    あなたは
    0.94
     youre
    0.87
    你自己
    0.86
     você
    0.82
     نفسك
    0.82
     bạn
    0.80
     máte
    0.80
     Yourself
    0.80
    Act Density 0.071%

    No Known Activations