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

    Neuronpedia

    INDEX
    Explanations

    product and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ἢ
    0.42
    믈
    0.39
     جلو
    0.39
    isierten
    0.39
    キム
    0.38
    ھیں
    0.38
     Guthrie
    0.38
    ทั่ว
    0.38
    ির্ব
    0.38
     aliquot
    0.37
    POSITIVE LOGITS
     Our
    0.53
    Our
    0.50
     wanted
    0.43
     want
    0.41
     product
    0.41
     싶
    0.41
    product
    0.40
    Styles
    0.40
    Product
    0.39
     belongs
    0.38
    Act Density 0.000%

    No Known Activations