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

    Neuronpedia

    INDEX
    Explanations

    availability to provide information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اسم
    0.41
     macro
    0.41
    urndata
    0.40
     searchQuery
    0.38
    roidism
    0.38
    ائم
    0.38
     acidosis
    0.38
    UTIONS
    0.37
    ipients
    0.37
     réflex
    0.37
    POSITIVE LOGITS
    讀
    0.41
    InputNum
    0.39
    ambe
    0.39
    如图
    0.38
    يال
    0.37
     Input
    0.37
    複雜
    0.36
     ਮੁ
    0.36
     sobre
    0.35
    史上
    0.35
    Act Density 0.001%

    No Known Activations