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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    State
    -0.07
    意愿
    -0.07
    arter
    -0.07
     "[%
    -0.07
     وأ
    -0.07
     preferences
    -0.07
    	events
    -0.07
    发动
    -0.07
    基础知识
    -0.07
    /App
    -0.07
    POSITIVE LOGITS
    他们的
    0.07
    iferay
    0.07
     בכתב
    0.07
    .Re
    0.07
    鄗
    0.07
     xấu
    0.07
    _retry
    0.06
    诧
    0.06
    ちら
    0.06
    Usually
    0.06
    Act Density 0.004%

    No Known Activations