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

    Neuronpedia

    INDEX
    Explanations

    numbers and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Random
    0.51
     intran
    0.49
     andre
    0.48
     überhaupt
    0.45
     Nase
    0.45
     vů
    0.44
     alé
    0.44
     Ré
    0.43
     éch
    0.43
     eins
    0.42
    POSITIVE LOGITS
     sixty
    0.84
     six
    0.71
     ६
    0.70
     шесть
    0.69
     шести
    0.69
     fifty
    0.68
     ಸುಮ
    0.68
     około
    0.66
    6
    0.64
     Sixty
    0.62
    Act Density 0.172%

    No Known Activations