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

    Neuronpedia

    INDEX
    Explanations

    numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    लंघन
    0.25
    وضوع
    0.24
    اونلو
    0.24
    پیگنڈ
    0.24
    颍
    0.24
    ائیگی
    0.24
    اعری
    0.24
    ల్ల
    0.23
    гүнкү
    0.23
    肿瘤
    0.23
    POSITIVE LOGITS
    0
    0.33
    7
    0.31
    5
    0.30
    u
    0.30
    6
    0.30
    9
    0.29
    i
    0.28
    8
    0.27
    +
    0.27
    ,
    0.27
    Act Density 0.114%

    No Known Activations