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

    Neuronpedia

    INDEX
    Explanations

    pre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    细细
    -0.08
    .tpl
    -0.07
    .Views
    -0.07
     x
    -0.07
    总公司
    -0.07
    สำรวจ
    -0.07
    ﴰ
    -0.07
    \Collection
    -0.07
    /meta
    -0.07
    <x
    -0.07
    POSITIVE LOGITS
    quí
    0.07
    𝙍
    0.07
    义
    0.07
    .ham
    0.07
     reunion
    0.07
    .Player
    0.07
    �
    0.07
    عظ
    0.06
    FSIZE
    0.06
    =''↵
    0.06
    Act Density 0.003%

    No Known Activations