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

    Neuronpedia

    INDEX
    Explanations

    soccer awards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aesthetic
    -0.07
     Thur
    -0.07
    活
    -0.07
    auss
    -0.06
    ضا
    -0.06
    -ion
    -0.06
    应该
    -0.06
    っている
    -0.06
     Tok
    -0.06
    onn
    -0.06
    POSITIVE LOGITS
    oại
    0.07
    %");↵
    0.07
    /******/↵
    0.07
     ++;↵
    0.06
    ýval
    0.06
    GLOBALS
    0.06
    \AppData
    0.06
     outline
    0.06
     AG
    0.06
    _enter
    0.06
    Act Density 0.015%

    No Known Activations