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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בחשבון
    -0.07
    comput
    -0.07
     несколько
    -0.07
    -delete
    -0.07
    と思
    -0.07
    为广大
    -0.07
     nbr
    -0.07
    ivers
    -0.07
    	min
    -0.07
     restarting
    -0.07
    POSITIVE LOGITS
     Кол
    0.08
    idences
    0.07
    �
    0.07
    隅
    0.07
    Off
    0.07
    浍
    0.07
    Ӓ
    0.07
     celery
    0.07
    �
    0.07
    Away
    0.06
    Act Density 0.006%

    No Known Activations