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

    Neuronpedia

    INDEX
    Explanations

    compressed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ç¼ĸ
    -0.28
    为åħ¶
    -0.26
     Alleg
    -0.25
    为èĩªå·±
    -0.25
    äºĮæľŁ
    -0.24
    aldo
    -0.24
    æ£Ģç´¢
    -0.24
    ç»Ļèĩªå·±
    -0.24
    uously
    -0.23
     çı
    -0.23
    POSITIVE LOGITS
    å½¢
    0.27
     Wilkinson
    0.27
    åģļå®Į
    0.26
    obl
    0.26
    bang
    0.25
    ç³Ĭæ¶Ĥ
    0.24
    VECTOR
    0.24
    bes
    0.24
    èģª
    0.23
    EC
    0.23
    Act Density 0.117%

    No Known Activations