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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pastry
    -0.07
     syncing
    -0.07
     Bud
    -0.06
     [=[
    -0.06
    associ
    -0.06
     restaurants
    -0.06
    parse
    -0.06
     poplat
    -0.06
     Arc
    -0.06
     پیوند
    -0.06
    POSITIVE LOGITS
     Obj
    0.07
     grátis
    0.07
     quake
    0.07
    ाभ
    0.07
    ANI
    0.06
    (res
    0.06
    куп
    0.06
     Booker
    0.06
    кт
    0.06
     gost
    0.06
    Act Density 0.013%

    No Known Activations