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

    Neuronpedia

    INDEX
    Explanations

    article publishing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egot
    -0.07
     içerisinde
    -0.07
     enticing
    -0.07
    담
    -0.06
    angu
    -0.06
     Lessons
    -0.06
    }:${
    -0.06
     Những
    -0.06
     condominium
    -0.06
    ḇ
    -0.06
    POSITIVE LOGITS
    ********************************************************************************
    0.07
    пря
    0.07
     hypoc
    0.07
    ='".$
    0.07
    ewart
    0.06
    希尔
    0.06
    YST
    0.06
    .collections
    0.06
    arak
    0.06
    :^
    0.06
    Act Density 0.009%

    No Known Activations