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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    述职
    -0.07
     مليون
    -0.07
    ")!=
    -0.06
    imen
    -0.06
     Indiana
    -0.06
    单项
    -0.06
     conseg
    -0.06
    的一个
    -0.06
    (mp
    -0.06
    ⮟
    -0.06
    POSITIVE LOGITS
    �
    0.07
    발
    0.07
     dismay
    0.07
    _AUT
    0.07
    \CMS
    0.07
     wxT
    0.06
    .Require
    0.06
    午餐
    0.06
    愉快
    0.06
     ApplicationException
    0.06
    Act Density 0.011%

    No Known Activations