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

    Neuronpedia

    INDEX
    Explanations

    quantities or percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grammaticality
    0.41
     ডাক্তারের
    0.39
    県の
    0.38
    缀
    0.38
     Englishman
    0.37
     indiqué
    0.37
     Maschine
    0.37
     Whose
    0.37
     Enlightenment
    0.36
     "--
    0.36
    POSITIVE LOGITS
     mayoría
    0.42
     majority
    0.39
     majorité
    0.38
     absolutamente
    0.38
    majority
    0.37
     większość
    0.37
     voto
    0.37
    makers
    0.36
     қили
    0.35
     miliardi
    0.35
    Act Density 0.001%

    No Known Activations