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

    Neuronpedia

    INDEX
    Explanations

    5 or 7

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ixon
    -0.07
    新产品
    -0.07
    쳤
    -0.07
    ws
    -0.07
    ດ
    -0.07
    atrix
    -0.07
    ⵜ
    -0.07
     remotely
    -0.07
    /reference
    -0.07
     Expo
    -0.06
    POSITIVE LOGITS
     AUT
    0.07
    '])){↵
    0.07
    蚂蚁
    0.07
     administrators
    0.07
     Paras
    0.07
     reven
    0.07
    疲惫
    0.07
    []{↵
    0.07
    岁时
    0.07
    "])){↵
    0.07
    Act Density 0.001%

    No Known Activations