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

    Neuronpedia

    INDEX
    Explanations

    what is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Emple
    0.37
    рования
    0.36
    ставить
    0.35
    жными
    0.35
    дання
    0.34
     utwor
    0.34
    नी
    0.34
    надцати
    0.34
    ઝા
    0.34
    зер
    0.34
    POSITIVE LOGITS
     makin
    0.39
     कोश
    0.36
     व्याकरण
    0.35
     Important
    0.34
    詁
    0.34
     важ
    0.34
     ಒಳ್ಳೆಯ
    0.34
    很多人
    0.34
     μαύ
    0.34
     mathematics
    0.33
    Act Density 0.120%

    No Known Activations