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

    Neuronpedia

    INDEX
    Explanations

    wearing specific clothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тэй
    0.92
    ます
    0.87
    док
    0.86
    Ν
    0.86
     Pp
    0.84
     Nomination
    0.83
    ди
    0.83
     Interestingly
    0.83
     CGFloat
    0.82
     concedes
    0.82
    POSITIVE LOGITS
    im
    1.10
    ir
    1.09
    ud
    1.09
    profiss
    1.09
     underwear
    1.05
     मतगणना
    1.05
     camiseta
    1.03
    อนไลน์
    1.03
     condimentum
    1.00
    għ
    0.99
    Act Density 0.002%

    No Known Activations