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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .TestCase
    -0.07
    月以来
    -0.07
    queda
    -0.07
    生涯
    -0.06
    以來
    -0.06
    bable
    -0.06
    烦恼
    -0.06
     america
    -0.06
    来说
    -0.06
    瑪
    -0.06
    POSITIVE LOGITS
     goodies
    0.07
    _local
    0.07
     Gratuit
    0.07
    .rd
    0.07
    -----↵
    0.06
     awesome
    0.06
    꾐
    0.06
     Aut
    0.06
     atroc
    0.06
    不用
    0.06
    Act Density 0.026%

    No Known Activations