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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns and interrogative starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fouls
    0.52
     vassals
    0.51
     inoltre
    0.48
     edibles
    0.48
     folds
    0.47
     fonctionnal
    0.47
     mods
    0.46
     adicional
    0.46
     grinders
    0.46
     incluye
    0.46
    POSITIVE LOGITS
    这是
    0.65
     هذا
    0.58
    這是
    0.58
    This
    0.57
     Ovaj
    0.56
    这是一个
    0.55
     दरअसल
    0.55
    안녕하세요
    0.54
     questo
    0.54
    是我们
    0.54
    Act Density 0.176%

    No Known Activations