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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns in several languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uling
    0.80
    yl
    0.73
    ﻏ
    0.72
    AMA
    0.65
     tán
    0.65
     contag
    0.64
    лим
    0.64
     Glut
    0.64
    Julia
    0.63
    uli
    0.62
    POSITIVE LOGITS
     onun
    1.18
     его
    1.11
    彼の
    1.08
    它的
    1.07
     jego
    1.06
     তাহাদিগের
    1.05
     deren
    1.05
     onların
    1.05
    他的
    1.04
     jeho
    1.04
    Act Density 0.316%

    No Known Activations