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

    Neuronpedia

    INDEX
    Explanations

    pronoun objects after actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     teie
    0.50
     your
    0.49
     our
    0.48
     votre
    0.46
     unsere
    0.46
     awọn
    0.43
    今回の
    0.42
    向けの
    0.42
     nosso
    0.41
    ファイルの
    0.41
    POSITIVE LOGITS
     it
    1.62
    它
    1.52
    它们
    1.36
     ĝi
    1.36
     اسے
    1.35
     તેને
    1.30
     它
    1.28
     them
    1.25
     них
    1.19
    them
    1.13
    Act Density 0.539%

    No Known Activations