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

    Neuronpedia

    INDEX
    Explanations

    multiple sheets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    かなり
    0.46
    ದ
    0.46
    Б
    0.44
    legend
    0.44
    ব
    0.43
    ಂಚ
    0.41
    ف
    0.41
    The
    0.40
    organizations
    0.40
    ಮ
    0.40
    POSITIVE LOGITS
     realizar
    0.51
     oración
    0.49
     sendo
    0.47
     bunu
    0.47
     slik
    0.47
     fazem
    0.47
     fazendo
    0.46
     participe
    0.46
     выполнить
    0.46
     valour
    0.46
    Act Density 0.009%

    No Known Activations