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

    Neuronpedia

    INDEX
    Explanations

    any type or kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出
    0.47
     đây
    0.44
     Punishment
    0.43
    াতাড়ি
    0.43
    6
    0.43
    引き
    0.42
     xuất
    0.41
    out
    0.41
     out
    0.41
    4
    0.39
    POSITIVE LOGITS
    类型的
    0.64
     soorten
    0.63
     types
    0.61
     유형
    0.60
     분야
    0.57
    类型
    0.56
    ประเภท
    0.56
    领域的
    0.55
     jenis
    0.54
     نوع
    0.54
    Act Density 0.000%

    No Known Activations