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

    Neuronpedia

    INDEX
    Explanations

    possessive and reciprocal relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     নিজেকে
    1.11
     himself
    1.08
     নিজেই
    0.95
     sozinho
    0.95
     his
    0.94
     নিজেও
    0.94
    他的
    0.93
     jego
    0.89
    ſelf
    0.87
     নিজে
    0.86
    POSITIVE LOGITS
    各自
    2.40
     nhau
    2.03
     leurs
    1.99
     saling
    1.96
    กัน
    1.92
    それぞれ
    1.89
     birbir
    1.88
    彼此
    1.86
     Their
    1.83
     서로
    1.83
    Act Density 0.155%

    No Known Activations