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

    Neuronpedia

    INDEX
    Explanations

    Ar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bien
    -0.08
    一笑
    -0.08
    blob
    -0.08
    (Block
    -0.08
    diet
    -0.07
    秘密
    -0.07
    Answers
    -0.07
     blessing
    -0.07
    Vote
    -0.07
    azel
    -0.07
    POSITIVE LOGITS
     unw
    0.08
    Ar
    0.08
    形
    0.07
     çekil
    0.07
    犰
    0.07
    햠
    0.07
    operator
    0.07
     Ar
    0.07
    下载
    0.07
    压缩
    0.07
    Act Density 0.032%

    No Known Activations