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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    forg
    -0.08
    オス
    -0.08
     electromagnetic
    -0.07
    Ars
    -0.07
    མ
    -0.07
    бир
    -0.07
    敷
    -0.07
    สนใจ
    -0.07
    過ぎ
    -0.07
     exclusively
    -0.07
    POSITIVE LOGITS
     ścian
    0.07
     sayı
    0.07
     Kend
    0.07
     Busy
    0.07
     Y
    0.06
    ��
    0.06
    」
    0.06
    "a
    0.06
     ioctl
    0.06
    攻击
    0.06
    Act Density 0.002%

    No Known Activations