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

    Neuronpedia

    INDEX
    Explanations

    re

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FA
    -0.08
    یست
    -0.07
     крок
    -0.07
    ляем
    -0.07
     〈
    -0.06
    ircular
    -0.06
     diplomats
    -0.06
     Bethesda
    -0.06
    AX
    -0.06
    opes
    -0.06
    POSITIVE LOGITS
     Presenter
    0.06
     dishwasher
    0.06
    이고
    0.06
    stdout
    0.06
    mdb
    0.06
    snd
    0.06
     руки
    0.06
     trov
    0.06
     quicker
    0.06
     cô
    0.06
    Act Density 0.003%

    No Known Activations