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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    春季
    -0.07
    sdale
    -0.06
    .componentInstance
    -0.06
    舐
    -0.06
    ◞
    -0.06
    承德
    -0.06
     asleep
    -0.06
    _SELF
    -0.06
    止损
    -0.06
    AGING
    -0.06
    POSITIVE LOGITS
    Declare
    0.08
    .twitch
    0.07
    דא
    0.07
    /mac
    0.07
     enums
    0.07
    _GAP
    0.07
    пуб
    0.07
    loc
    0.07
    .IO
    0.07
     بالأ
    0.06
    Act Density 0.016%

    No Known Activations