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

    Neuronpedia

    INDEX
    Explanations

    material specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     membawa
    0.46
    пустить
    0.46
     можна
    0.45
     menyaksikan
    0.42
     можно
    0.39
     paint
    0.39
     क्रा
    0.39
    gunakan
    0.38
     badly
    0.37
     memberikan
    0.37
    POSITIVE LOGITS
    7
    0.48
    8
    0.46
    ある
    0.46
     longiore
    0.45
    したのは
    0.44
    4
    0.44
    如果是
    0.44
    男性
    0.43
     그런데
    0.43
     aliqua
    0.41
    Act Density 0.001%

    No Known Activations