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

    Neuronpedia

    INDEX
    Explanations

    qualifier followed by concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     साइकिल
    0.43
    si
    0.41
    等多
    0.39
     esempi
    0.39
     चॉकलेट
    0.39
     엔
    0.38
     anschließend
    0.38
     demokrat
    0.37
    ここでは
    0.37
    ền
    0.37
    POSITIVE LOGITS
     utilize
    0.43
    اريات
    0.41
    storeItem
    0.40
     exotic
    0.39
    利用
    0.38
    interaction
    0.38
    歌曲
    0.38
    converted
    0.38
    ʙ
    0.38
    интере
    0.38
    Act Density 0.000%

    No Known Activations