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

    Neuronpedia

    INDEX
    Explanations

    letters and reminders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Нет
    0.42
     where
    0.40
     piloting
    0.38
     startling
    0.38
    One
    0.38
    ួល
    0.38
     focused
    0.37
    ீர
    0.37
    ຜ
    0.37
    elling
    0.36
    POSITIVE LOGITS
     prieš
    0.43
     quizá
    0.43
    ]/
    0.42
     церков
    0.41
    不錯
    0.39
     Geschichte
    0.39
    otoxin
    0.38
    АО
    0.38
    সুর
    0.38
    优秀的
    0.38
    Act Density 0.000%

    No Known Activations