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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crumbling
    -0.06
    	fill
    -0.06
    iou
    -0.06
    material
    -0.06
     rg
    -0.06
     cig
    -0.06
    	load
    -0.06
    旅
    -0.06
     Django
    -0.06
     cev
    -0.06
    POSITIVE LOGITS
     xrange
    0.07
    합니다
    0.07
    (INT
    0.06
    อาย
    0.06
    ۲۰۲
    0.06
     Zucker
    0.06
     شدند
    0.06
    xlim
    0.06
     '*.
    0.06
    幸
    0.06
    Act Density 0.159%

    No Known Activations