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

    Neuronpedia

    INDEX
    Explanations

    affirmations and certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可能会
    0.61
     potencialmente
    0.60
    可能會
    0.59
    可能
    0.59
     可能
    0.59
     potentially
    0.58
    かもしれません
    0.56
     อาจ
    0.54
     может
    0.53
     возмо
    0.53
    POSITIVE LOGITS
     clearly
    1.94
     unequivocally
    1.80
    clearly
    1.77
     claramente
    1.73
     unambiguously
    1.71
    Clearly
    1.67
     obvious
    1.66
     unmistak
    1.66
     Clearly
    1.63
     unquestionably
    1.63
    Act Density 0.022%

    No Known Activations