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

    Neuronpedia

    INDEX
    Explanations

    Foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    沃
    -0.07
    湔
    -0.07
    埤
    -0.07
     conta
    -0.07
    zion
    -0.07
     Expect
    -0.07
    鄞
    -0.07
     canada
    -0.07
    忿
    -0.07
    نسخ
    -0.07
    POSITIVE LOGITS
    中国人民
    0.08
     вн
    0.07
    	person
    0.07
     дальн
    0.07
    軟
    0.07
    	M
    0.06
    од
    0.06
     (_
    0.06
    记者表示
    0.06
     Increased
    0.06
    Act Density 0.027%

    No Known Activations