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

    Neuronpedia

    INDEX
    Explanations

    assist with, focus on, interferes with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     этом
    0.42
    %.
    0.41
    这种
    0.40
    。
    0.40
     αυτή
    0.39
     ہے۔
    0.39
    ):
    0.39
     ہوگا۔
    0.38
    attro
    0.38
     настолько
    0.38
    POSITIVE LOGITS
    !,
    0.56
     എന്നിവ
    0.46
    했고
    0.46
    ?,
    0.46
     €,
    0.45
     തുടങ്ങി
    0.44
     없고
    0.44
     തുടങ്ങിയ
    0.44
     എന്നീ
    0.43
    +,
    0.43
    Act Density 0.439%

    No Known Activations