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

    Neuronpedia

    INDEX
    Explanations

    certain given particular

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    你能
    0.40
    所有人
    0.40
    jeća
    0.40
     तलाश
    0.39
     ನೀವು
    0.39
     トップス
    0.39
     શક્ય
    0.38
     estima
    0.38
    ກະ
    0.38
    你不
    0.38
    POSITIVE LOGITS
     particular
    0.59
     certain
    0.56
     ciertas
    0.55
    Certain
    0.50
     bepaalde
    0.48
     versus
    0.48
     주어진
    0.46
     различных
    0.46
     bestimmten
    0.46
     Certain
    0.45
    Act Density 0.235%

    No Known Activations