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

    Neuronpedia

    INDEX
    Explanations

    vertical alignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    免责
    -0.07
    unset
    -0.07
    랖
    -0.07
    迓
    -0.07
    实施细则
    -0.06
    regon
    -0.06
    >Delete
    -0.06
    _EXIT
    -0.06
    탭
    -0.06
     taxing
    -0.06
    POSITIVE LOGITS
    后
    0.07
    Estimated
    0.07
     :
↵
    0.07
     الفور
    0.07
    movies
    0.07
    斯顿
    0.06
    ופ
    0.06
    	s
    0.06
     FOOT
    0.06
    ف
    0.06
    Act Density 0.036%

    No Known Activations