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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     annunci
    -0.07
    latlong
    -0.07
    桂
    -0.07
     cultivated
    -0.07
     exploited
    -0.07
     바이
    -0.06
    ุงเทพมหานคร
    -0.06
    บาท
    -0.06
    หนอง
    -0.06
    ями
    -0.06
    POSITIVE LOGITS
    :-
    0.06
    ımızı
    0.06
    	friend
    0.06
    ="-
    0.06
     web
    0.06
    !
    0.06
    iens
    0.06
    AL
    0.06
    /sql
    0.06
    iken
    0.06
    Act Density 0.000%

    No Known Activations