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

    Neuronpedia

    INDEX
    Explanations

    does

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vapor
    -0.07
     PC
    -0.06
    riends
    -0.06
    	 
↵
    -0.06
     railway
    -0.06
     embraced
    -0.06
    archive
    -0.06
     Corp
    -0.06
     meditation
    -0.06
     رابطه
    -0.06
    POSITIVE LOGITS
     التش
    0.07
    .REG
    0.07
    出品
    0.06
     LOWER
    0.06
    ุนายน
    0.06
     fikir
    0.06
    RouterModule
    0.06
    들도
    0.06
    님이
    0.06
     대행
    0.06
    Act Density 0.155%

    No Known Activations