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

    Neuronpedia

    INDEX
    Explanations

    State

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    빙
    -0.06
     Marines
    -0.06
     uomini
    -0.06
     سي
    -0.06
    川
    -0.06
    孩子
    -0.06
     grav
    -0.06
    맹
    -0.06
    จะเป
    -0.06
    фектив
    -0.06
    POSITIVE LOGITS
    Hol
    0.07
    ISHED
    0.07
    _PERIOD
    0.06
    ScreenState
    0.06
    ヌ
    0.06
    eldon
    0.06
    (single
    0.06
    (mContext
    0.06
     Looking
    0.06
    langle
    0.06
    Act Density 0.001%

    No Known Activations