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

    Neuronpedia

    INDEX
    Explanations

    find-help links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cript
    0.67
    वर्ती
    0.67
     xin
    0.65
    list
    0.62
    гер
    0.62
     ({
    0.60
     script
    0.58
    ionista
    0.56
     причем
    0.56
    istan
    0.55
    POSITIVE LOGITS
     Programs
    0.90
    भाल
    0.89
    知識
    0.88
     CONTENT
    0.87
     Content
    0.86
    Content
    0.86
    工夫
    0.84
     Webinar
    0.82
    Programs
    0.82
     Barang
    0.81
    Act Density 0.103%

    No Known Activations