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

    Neuronpedia

    INDEX
    Explanations

    department

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Гер
    -0.07
    verified
    -0.07
     ボ
    -0.06
     Shotgun
    -0.06
     Nguyễn
    -0.06
    lobby
    -0.06
    currentUser
    -0.06
    Lewis
    -0.06
    (pDX
    -0.05
     enthusi
    -0.05
    POSITIVE LOGITS
     없이
    0.08
    _mov
    0.07
     #↵
    0.07
     untuk
    0.07
     이제
    0.07
     hopefully
    0.07
    (fn
    0.07
    лаг
    0.07
    ibrary
    0.07
    (close
    0.07
    Act Density 0.001%

    No Known Activations