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

    Neuronpedia

    INDEX
    Explanations

    description:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BOOK
    0.44
     CheckException
    0.44
    𝗢
    0.42
    FileList
    0.41
     היו
    0.40
     QnrB
    0.39
     BOOK
    0.39
    寞
    0.39
    Ὑ
    0.39
     Приступ
    0.39
    POSITIVE LOGITS
     이용해서
    0.52
    ونم
    0.44
    ช่วง
    0.44
    ！」
    0.42
     afgelopen
    0.42
     három
    0.41
    ää
    0.41
     gemidd
    0.41
    ти
    0.40
    ні
    0.40
    Act Density 0.001%

    No Known Activations