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

    Neuronpedia

    INDEX
    Explanations

    phrases from riddles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಆ
    0.48
    ----\
    0.47
    因
    0.47
    佲
    0.47
     كافة
    0.45
     estudiantes
    0.45
    вич
    0.45
     جميع
    0.43
    入了
    0.43
    ্টি
    0.43
    POSITIVE LOGITS
     postcards
    0.49
     Firmen
    0.49
     Fossil
    0.45
     baz
    0.44
    bal
    0.44
     condiment
    0.44
     Vinyl
    0.44
    t
    0.44
     Salon
    0.43
    firma
    0.43
    Act Density 0.001%

    No Known Activations