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

    Neuronpedia

    INDEX
    Explanations

    we are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    自分が
    0.67
     নিজেকে
    0.61
    自分の
    0.59
     himself
    0.59
     자신의
    0.58
     자신이
    0.55
    我的
    0.55
     نفسه
    0.55
     নিজে
    0.53
     తాను
    0.53
    POSITIVE LOGITS
     ourselves
    1.28
     आहोत
    0.77
     છીએ
    0.76
     oynuyoruz
    0.75
     хотим
    0.74
     знаем
    0.74
     giriyoruz
    0.70
    ogliamo
    0.69
     можем
    0.68
     fizemos
    0.65
    Act Density 0.112%

    No Known Activations