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

    Neuronpedia

    INDEX
    Explanations

    academic terms, programming, and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     componentes
    0.43
     değiştir
    0.41
    fordert
    0.40
     दिवसा
    0.40
    проце
    0.39
    তীশ
    0.39
     schreiben
    0.38
    muslim
    0.38
    риса
    0.38
    Gui
    0.38
    POSITIVE LOGITS
     across
    0.41
     etc
    0.41
     atk
    0.39
    反复
    0.38
    辄
    0.38
    වු
    0.38
    嶅
    0.37
     approx
    0.37
     impl
    0.37
    inkler
    0.37
    Act Density 0.003%

    No Known Activations