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

    Neuronpedia

    INDEX
    Explanations

    Japanese names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tensorflow
    1.07
     Hunan
    1.07
     Ubisoft
    1.04
     Minsk
    1.02
     Yuan
    1.01
     WeChat
    1.00
     Uygh
    1.00
     Confucian
    0.99
     Irland
    0.99
     Sichuan
    0.99
    POSITIVE LOGITS
     א
    0.89
     स
    0.83
    三
    0.76
     י
    0.75
    新
    0.72
    小
    0.70
     פ
    0.70
     ר
    0.69
    一
    0.66
     ג
    0.65
    Act Density 0.049%

    No Known Activations