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

    Neuronpedia

    INDEX
    Explanations

    asking name and favorites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    楽曲
    0.54
     Recordemos
    0.46
    を用いた
    0.44
    ègre
    0.44
     Folks
    0.43
    ówczas
    0.41
     ลักษณะ
    0.40
    த்துள்ளது
    0.40
     lediglich
    0.39
     Ultimately
    0.38
    POSITIVE LOGITS
     kinda
    0.70
     idk
    0.63
     stuff
    0.60
     awesome
    0.59
     stupid
    0.59
     dudes
    0.59
     weird
    0.58
     dude
    0.58
     sorta
    0.58
     poop
    0.57
    Act Density 0.022%

    No Known Activations