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
     আমাকে
    0.71
     моих
    0.66
     minhas
    0.65
    我的
    0.63
     मुझसे
    0.60
     मेरा
    0.57
    私の
    0.57
     ನನಗೆ
    0.57
     yourself
    0.56
     мои
    0.56
    POSITIVE LOGITS
     ourselves
    1.50
     आहोत
    1.07
     نحن
    0.88
     oynuyoruz
    0.88
     хотим
    0.87
     talking
    0.86
     можем
    0.86
     છીએ
    0.86
     giriyoruz
    0.86
     знаем
    0.84
    Act Density 0.017%

    No Known Activations