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

    Neuronpedia

    INDEX
    Explanations

    returning home

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commented
    -0.07
    비스
    -0.07
     userinfo
    -0.07
    .cleanup
    -0.07
    _dup
    -0.06
     karşı
    -0.06
    筦
    -0.06
     /****************************************************************
    -0.06
     entertain
    -0.06
    .getModel
    -0.06
    POSITIVE LOGITS
    ={
    0.07
    蟥
    0.07
    -priced
    0.07
    髅
    0.07
     $('
    0.06
    .newLine
    0.06
     Rank
    0.06
    鳞
    0.06
    拜访
    0.06
    腰部
    0.06
    Act Density 0.034%

    No Known Activations