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

    Neuronpedia

    INDEX
    Explanations

    title for article, movie, song

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    른
    0.47
    embangkan
    0.47
    ثمان
    0.44
    互联网档案馆
    0.44
    سٹم
    0.44
     چھوٹے
    0.42
    udsman
    0.41
    يدات
    0.41
    Renk
    0.41
    ेंसिल
    0.41
    POSITIVE LOGITS
    %'
    0.48
     ob
    0.43
     brief
    0.43
    De
    0.39
     units
    0.39
     ve
    0.39
     abrupt
    0.39
    Brief
    0.39
    ゾ
    0.39
     ro
    0.38
    Act Density 0.001%

    No Known Activations