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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tourism
    -0.08
    天赋
    -0.07
    기도
    -0.07
    油脂
    -0.07
    ircuit
    -0.07
     amateur
    -0.07
    Shared
    -0.07
    相信大家
    -0.07
    いたら
    -0.07
     UserData
    -0.07
    POSITIVE LOGITS
     ere
    0.07
    煲
    0.07
    .Root
    0.07
    릅
    0.07
     aggregate
    0.07
    .demo
    0.07
    베
    0.06
     seedu
    0.06
    龋
    0.06
     fractures
    0.06
    Act Density 0.003%

    No Known Activations