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

    Neuronpedia

    INDEX
    Explanations

    LIFESTAGE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เบียน
    0.43
    聵
    0.42
    应用于
    0.41
     העולם
    0.40
    ribution
    0.39
    ષ્ટ
    0.38
     חלק
    0.38
     intimately
    0.37
    דרך
    0.37
     دنی
    0.37
    POSITIVE LOGITS
     LR
    0.46
     Jacq
    0.43
    sta
    0.41
     BOW
    0.41
     CR
    0.41
    ە
    0.41
    roep
    0.41
     ESD
    0.40
     kontrol
    0.40
     XPS
    0.40
    Act Density 0.000%

    No Known Activations