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

    Neuronpedia

    INDEX
    Explanations

    Rounding numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    关于我们
    -0.07
    王子
    -0.07
     Возможно
    -0.07
    增加
    -0.07
     maybe
    -0.07
     }↵
    -0.07
    全方位
    -0.06
    umberland
    -0.06
     essere
    -0.06
    All
    -0.06
    POSITIVE LOGITS
    .Ok
    0.08
    �
    0.07
    _Select
    0.07
     Vac
    0.07
    맫
    0.07
     privately
    0.07
    forcement
    0.07
    irting
    0.07
    (parsed
    0.07
    .inner
    0.07
    Act Density 0.015%

    No Known Activations