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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curing
    -0.07
     pathogens
    -0.06
     іде
    -0.06
     الات
    -0.06
     illegally
    -0.06
     tabs
    -0.06
    jobs
    -0.06
    .collection
    -0.06
     importantes
    -0.06
    ٣
    -0.06
    POSITIVE LOGITS
    ","\
    0.07
    =_("
    0.06
    -----------*/↵
    0.06
    (ang
    0.06
    هه
    0.06
    ージ
    0.06
     RTBU
    0.06
     Một
    0.06
     Restaurant
    0.06
    ,True
    0.06
    Act Density 0.003%

    No Known Activations