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

    Neuronpedia

    INDEX
    Explanations

    singular answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    実は
    0.77
    ちょっと
    0.75
     Кстати
    0.72
     многи
    0.72
     многих
    0.71
    we
    0.71
    私たちは
    0.70
     эксплуатации
    0.70
     훨씬
    0.67
     heyday
    0.67
    POSITIVE LOGITS
     formatted
    1.39
     sentences
    1.36
     concise
    1.29
     replying
    1.27
     sentence
    1.25
     succinct
    1.24
     respostas
    1.22
     answers
    1.22
    回答
    1.20
     answer
    1.20
    Act Density 1.554%

    No Known Activations