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

    Neuronpedia

    INDEX
    Explanations

    Academic subjects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     delightful
    -0.06
     фінанс
    -0.06
    AINER
    -0.06
     uh
    -0.06
    mlin
    -0.06
    카라
    -0.06
    Karen
    -0.06
     ．
    -0.06
     Кур
    -0.06
     fearing
    -0.06
    POSITIVE LOGITS
     гем
    0.07
     conscience
    0.07
     DIFF
    0.06
    _TRACK
    0.06
    ,column
    0.06
     trans
    0.06
     cname
    0.06
     invoked
    0.06
    amientos
    0.06
    .Firebase
    0.06
    Act Density 0.180%

    No Known Activations