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

    Neuronpedia

    INDEX
    Explanations

    Russia, Crimea, Donbas conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    储备
    0.44
     purge
    0.40
    肾
    0.40
     secretNumber
    0.39
     demon
    0.39
     साम
    0.39
     Đáp
    0.39
     técn
    0.38
    做什么
    0.38
     Elim
    0.38
    POSITIVE LOGITS
    initial
    0.50
    lieder
    0.44
     stood
    0.41
    hemian
    0.41
    installer
    0.41
    iotensin
    0.41
    isdir
    0.41
    riminal
    0.40
    article
    0.40
    onski
    0.40
    Act Density 0.019%

    No Known Activations