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

    Neuronpedia

    INDEX
    Explanations

    parameter and console

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ⠀
    0.41
    ంటు
    0.38
     ‬
    0.38
    माम
    0.36
    सीसी
    0.35
     многим
    0.35
    ৈতিক
    0.35
    ⠀⠀
    0.35
    сеп
    0.35
    সর
    0.34
    POSITIVE LOGITS
    等的
    0.46
     enemy
    0.39
    ಲಿನ
    0.38
    莧
    0.38
    enemy
    0.37
     jung
    0.37
     وہی
    0.37
    苋
    0.37
    die
    0.36
     oaks
    0.36
    Act Density 0.287%

    No Known Activations