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

    Neuronpedia

    INDEX
    Explanations

    multilingual greetings and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.45
    -
    0.45
     expo
    0.42
    且
    0.42
     dev
    0.42
     fails
    0.41
     et
    0.40
     "
    0.39
     cos
    0.39
     hydro
    0.39
    POSITIVE LOGITS
    alamualaikum
    0.52
     Bienvenidos
    0.49
     yaşam
    0.45
    ektedir
    0.45
    人们
    0.45
     पीपल
    0.45
     ഹോളി
    0.44
     ngunit
    0.43
    登陆
    0.43
     oamenii
    0.43
    Act Density 0.005%

    No Known Activations