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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     следующие
    -0.07
     endereco
    -0.07
    !.↵↵
    -0.06
    ：↵
    -0.06
     گذاری
    -0.06
     basın
    -0.06
     přep
    -0.06
    	wx
    -0.06
    .')↵↵
    -0.06
    "]}↵
    -0.06
    POSITIVE LOGITS
    IGNED
    0.07
     Come
    0.06
     Hedge
    0.06
     Unknown
    0.06
    .met
    0.06
    Netflix
    0.06
     cra
    0.06
    SB
    0.06
     जम
    0.06
     Gust
    0.06
    Act Density 0.086%

    No Known Activations