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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     furthermore
    -0.07
    ㄴ
    -0.07
    Ошибка
    -0.07
     egt
    -0.07
    进了
    -0.07
     CU
    -0.06
    ￂ
    -0.06
    .Version
    -0.06
     информ
    -0.06
    .ms
    -0.06
    POSITIVE LOGITS
     chịu
    0.08
    amel
    0.08
    _reviews
    0.08
    百合
    0.08
    찯
    0.07
     standoff
    0.07
    랑
    0.07
     التابعة
    0.07
     tabBar
    0.07
    \Table
    0.07
    Act Density 0.007%

    No Known Activations