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

    Neuronpedia

    INDEX
    Explanations

    pronoun-verb contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    认为
    0.20
     These
    0.19
    、
    0.19
    ，
    0.18
    choose
    0.18
    認為
    0.18
     ,
    0.17
     considère
    0.17
    dealing
    0.17
    Са
    0.17
    POSITIVE LOGITS
     isn
    0.22
     είναι
    0.21
    จะไม่
    0.21
     brukes
    0.21
     есть
    0.20
     दिखने
    0.19
     není
    0.19
    াইব
    0.19
    ી
    0.19
     будет
    0.18
    Act Density 0.401%

    No Known Activations