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

    Neuronpedia

    INDEX
    Explanations

    code context or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мер
    0.80
     subsidi
    0.80
    什么是
    0.79
    erde
    0.78
     compresses
    0.78
    ্য
    0.78
     succesfully
    0.77
    稃
    0.76
     discharg
    0.76
     correlates
    0.75
    POSITIVE LOGITS
     ký
    0.86
     Jednak
    0.83
     rằng
    0.82
    usión
    0.80
     Ancak
    0.80
     وأن
    0.79
     Дэ
    0.79
     তাপ
    0.77
     Vé
    0.76
     Vulner
    0.76
    Act Density 0.000%

    No Known Activations