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

    Neuronpedia

    INDEX
    Explanations

    nouns following possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंबे
    0.39
    :</
    0.37
     দেখুনঃ
    0.36
     intricacies
    0.34
    ）・
    0.34
     ядра
    0.33
    ელი
    0.33
    ・
    0.33
    الب
    0.33
    ینده
    0.33
    POSITIVE LOGITS
     persönliche
    0.45
     has
    0.44
     son
    0.41
     persön
    0.40
     personal
    0.39
    takes
    0.39
     persoonlijke
    0.39
    个人的
    0.39
    dad
    0.38
     має
    0.38
    Act Density 0.020%

    No Known Activations