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

    Neuronpedia

    INDEX
    Explanations

    `ls`, `str`, `discriminator`, `statement`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.48
    Fre
    0.43
    0.41
     St
    0.40
     Mün
    0.39
     Sol
    0.38
    Thoughts
    0.38
     Col
    0.38
     اد
    0.38
     Amherst
    0.38
    POSITIVE LOGITS
     информация
    0.50
    ъ
    0.49
    UNK
    0.47
    មើ
    0.46
     attentively
    0.45
    ِيم
    0.44
     фигу
    0.44
    ’:
    0.44
    ਿਆਂ
    0.43
    你有
    0.43
    Act Density 0.006%

    No Known Activations