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

    Neuronpedia

    INDEX
    Explanations

    minutes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :)↵↵
    -0.07
     والع
    -0.07
     ;)↵↵
    -0.07
     leather
    -0.06
     الجم
    -0.06
    iệm
    -0.06
     знаю
    -0.06
     العلم
    -0.06
     معن
    -0.06
    _FRE
    -0.06
    POSITIVE LOGITS
    	dp
    0.06
    nsic
    0.06
     chron
    0.06
     Gust
    0.06
    Sus
    0.06
     corners
    0.06
     yeniden
    0.06
     forensic
    0.06
     adhere
    0.06
     Descriptor
    0.06
    Act Density 0.002%

    No Known Activations