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

    Neuronpedia

    INDEX
    Explanations

    structured lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sorting
    0.41
     einzelne
    0.39
    Sort
    0.38
    asign
    0.38
     chose
    0.38
     mousse
    0.38
     sorting
    0.37
    idiu
    0.37
     صوت
    0.36
    Entire
    0.35
    POSITIVE LOGITS
     list
    1.46
     список
    1.27
     списке
    1.26
     lista
    1.18
     सूची
    1.15
     قائمة
    1.12
     목록
    1.11
    名单
    1.10
    list
    1.09
     لیست
    1.06
    Act Density 0.025%

    No Known Activations