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

    Neuronpedia

    INDEX
    Explanations

    experimental group of people/animals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    备份
    -0.07
     Báo
    -0.07
    頁
    -0.07
     Tiến
    -0.07
    ropol
    -0.07
    开会
    -0.06
    爆料
    -0.06
    彝
    -0.06
    .piece
    -0.06
     joystick
    -0.06
    POSITIVE LOGITS
     אותי
    0.07
     resident
    0.07
    ucle
    0.06
     תמיד
    0.06
    Age
    0.06
     premiums
    0.06
    Cit
    0.06
    ś
    0.06
    תחומי
    0.06
     extends
    0.06
    Act Density 0.114%

    No Known Activations