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

    Neuronpedia

    INDEX
    Explanations

    representatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     br
    -0.07
    一字
    -0.07
     Tic
    -0.07
     Vor
    -0.07
     bart
    -0.07
    -big
    -0.07
    ."</
    -0.07
    向社会
    -0.07
    点缀
    -0.07
     goo
    -0.06
    POSITIVE LOGITS
    _yield
    0.08
    的には
    0.08
    QUEST
    0.07
    _tickets
    0.07
    lé
    0.07
    สำรวจ
    0.07
    attendance
    0.06
    _formula
    0.06
    IFICATIONS
    0.06
    空调
    0.06
    Act Density 0.023%

    No Known Activations