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

    Neuronpedia

    INDEX
    Explanations

    pronouns (they, them)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    珵
    0.79
    வில
    0.74
    iebel
    0.72
     పా
    0.72
    ரிக்க
    0.71
     coherent
    0.70
     replicates
    0.69
    一枚
    0.68
    破解
    0.68
    ılabilir
    0.68
    POSITIVE LOGITS
     them
    2.08
    them
    1.86
     них
    1.84
     they
    1.76
     они
    1.75
     ellos
    1.72
    they
    1.71
     вони
    1.66
     THEM
    1.54
     ihnen
    1.54
    Act Density 0.110%

    No Known Activations