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

    Neuronpedia

    INDEX
    Explanations

    lose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ycastle
    -0.07
    .network
    -0.06
    .adapters
    -0.06
    λει
    -0.06
    �
    -0.06
    梯
    -0.06
    uffled
    -0.06
    )}↵↵
    -0.06
     jointly
    -0.06
     khẩu
    -0.06
    POSITIVE LOGITS
    	Item
    0.07
    (stat
    0.06
    ioc
    0.06
    restaurant
    0.06
     Сам
    0.05
    仓
    0.05
    RAIN
    0.05
    tent
    0.05
    іль
    0.05
     Beginning
    0.05
    Act Density 0.575%

    No Known Activations