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

    Neuronpedia

    INDEX
    Explanations

    Science and research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    魔鬼
    -0.08
    天国继续
    -0.07
    蜒
    -0.07
     IOCTL
    -0.07
     weil
    -0.07
    ילות
    -0.07
     cigaret
    -0.07
     fake
    -0.07
     UIButton
    -0.07
     כאיל
    -0.06
    POSITIVE LOGITS
     parfait
    0.08
     france
    0.08
     Std
    0.07
     nxt
    0.07
    순
    0.07
     Merry
    0.07
     Spot
    0.07
    激
    0.07
     그리스
    0.07
     mah
    0.07
    Act Density 0.016%

    No Known Activations