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

    Neuronpedia

    INDEX
    Explanations

    more permanent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    馬上
    0.42
    すぐ
    0.41
    šić
    0.40
     сразу
    0.39
     சேர்ந்து
    0.39
     sitio
    0.38
     바로
    0.38
    Hib
    0.38
     Bd
    0.37
     meteen
    0.37
    POSITIVE LOGITS
    uture
    0.42
    ulate
    0.39
    予想
    0.39
    bate
    0.39
     skateboard
    0.38
     esti
    0.38
    迷
    0.38
     interpreta
    0.37
     STEAM
    0.37
     возду
    0.37
    Act Density 0.011%

    No Known Activations