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

    Neuronpedia

    INDEX
    Explanations

    mutual relationship between entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আমার
    0.52
     ತನ್ನ
    0.52
     получил
    0.48
     وی
    0.45
     নিজেই
    0.44
     त्याला
    0.43
     Marche
    0.43
    আমার
    0.43
     उसकी
    0.41
     받은
    0.41
    POSITIVE LOGITS
     서로
    1.33
     birbir
    1.24
    彼此
    1.19
     juntos
    1.18
    互相
    1.18
     mutual
    1.13
    相互
    1.13
     saling
    1.11
    各自
    1.09
     mutually
    1.09
    Act Density 0.230%

    No Known Activations