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

    Neuronpedia

    INDEX
    Explanations

    giải thích thuật ngữ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䧺
    0.43
    اؤ
    0.42
     باوجود
    0.40
     mutlaka
    0.40
     memberi
    0.40
    zwischen
    0.40
    র্মে
    0.39
    culture
    0.39
     Dienste
    0.39
     produisent
    0.38
    POSITIVE LOGITS
     correct
    0.47
    相关
    0.46
     문제
    0.44
    ：
    0.44
     correcta
    0.42
    慵
    0.41
    一下
    0.40
    如下
    0.40
    事情
    0.40
     adverb
    0.39
    Act Density 0.000%

    No Known Activations