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

    Neuronpedia

    INDEX
    Explanations

    Updates or announcements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elpers
    -0.07
    flowers
    -0.07
     helf
    -0.06
    Hash
    -0.06
    Visitor
    -0.06
    ault
    -0.06
    ıy
    -0.06
     qr
    -0.06
    Lim
    -0.06
    Alarm
    -0.06
    POSITIVE LOGITS
     Homes
    0.06
     kvinder
    0.06
    -carousel
    0.06
    UIViewController
    0.06
     joke
    0.06
     подаль
    0.06
     ensued
    0.06
    FUNCTION
    0.06
     Poe
    0.06
     AssemblyCopyright
    0.06
    Act Density 0.052%

    No Known Activations