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

    Neuronpedia

    INDEX
    Explanations

    Microsoft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PartialEq
    -0.07
     Gale
    -0.07
     Catholic
    -0.07
     Remarks
    -0.07
    pository
    -0.06
     Kart
    -0.06
     řád
    -0.06
    哲
    -0.06
     влия
    -0.06
     гли
    -0.06
    POSITIVE LOGITS
    něl
    0.07
    WARDED
    0.07
     advising
    0.07
    طع
    0.07
    ！」↵↵
    0.06
    .peer
    0.06
    ＼↵
    0.06
    واع
    0.06
    Manufacturer
    0.06
    ース
    0.06
    Act Density 0.003%

    No Known Activations