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

    Neuronpedia

    INDEX
    Explanations

    _engine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帛
    -0.08
    undra
    -0.06
     których
    -0.06
     العربية
    -0.06
    靠
    -0.06
    芥
    -0.06
    hiro
    -0.06
    马拉
    -0.06
    ừ
    -0.06
    ß
    -0.06
    POSITIVE LOGITS
    EC
    0.07
     setState
    0.07
     turbulent
    0.07
    🤵
    0.07
    &action
    0.06
     המשחק
    0.06
    �
    0.06
     cooldown
    0.06
    奔驰
    0.06
     Kate
    0.06
    Act Density 0.001%

    No Known Activations