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

    Neuronpedia

    INDEX
    Explanations

    be aware of or know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    會議
    0.40
    ongo
    0.39
    eper
    0.39
    uesthouse
    0.39
    pee
    0.39
     cetera
    0.37
    ো
    0.37
     terang
    0.37
    ettet
    0.37
    arge
    0.36
    POSITIVE LOGITS
     일반적으로
    0.55
     generell
    0.45
     ponieważ
    0.43
     większość
    0.42
     według
    0.41
     sämt
    0.41
     eine
    0.40
     Menurut
    0.40
     большинство
    0.40
     большин
    0.40
    Act Density 0.000%

    No Known Activations