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

    Neuronpedia

    INDEX
    Explanations

    currency conversion and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Its
    0.43
     무슨
    0.43
     роки
    0.41
     рейти
    0.40
    tores
    0.40
     заместитель
    0.40
    酔
    0.38
     qualche
    0.38
     destru
    0.38
     Its
    0.36
    POSITIVE LOGITS
     $
    0.47
    １
    0.46
     $\$
    0.45
     ۱
    0.44
     ১
    0.43
     £
    0.41
     १
    0.41
     ১০০
    0.41
     money
    0.39
     €
    0.39
    Act Density 0.001%

    No Known Activations