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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    俊
    -0.08
    Username
    -0.07
    抢救
    -0.07
    职业教育
    -0.07
     Citizen
    -0.07
     Chun
    -0.07
    ees
    -0.07
     entirely
    -0.07
    filename
    -0.07
    ecture
    -0.07
    POSITIVE LOGITS
    괴
    0.07
    Ｆ
    0.07
    눌
    0.07
    _parm
    0.07
    حم
    0.07
     Blanch
    0.06
     Manga
    0.06
     الأمريكي
    0.06
     Flatten
    0.06
    _singleton
    0.06
    Act Density 0.095%

    No Known Activations