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

    Neuronpedia

    INDEX
    Explanations

    content that AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.83
     অন্য
    0.77
    ó
    0.72
     थोडे
    0.71
     מאוד
    0.70
    ра
    0.68
     цвета
    0.68
     أحمد
    0.68
    carrot
    0.68
    まま
    0.66
    POSITIVE LOGITS
     emanating
    0.71
    יה
    0.67
     humaines
    0.66
    ɱ
    0.66
    τσι
    0.64
    lery
    0.63
     justiciable
    0.63
     discerning
    0.62
    Читати
    0.62
     giriyoruz
    0.61
    Act Density 0.001%

    No Known Activations