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

    Neuronpedia

    INDEX
    Explanations

    possessive pronoun 'their' and what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    你
    0.86
     você
    0.80
     тебе
    0.79
    是一個
    0.79
     budete
    0.79
    あなたは
    0.78
     ყველა
    0.78
     당신
    0.77
     you
    0.77
     yourself
    0.75
    POSITIVE LOGITS
     leurs
    2.11
     themselves
    2.02
     their
    1.99
    their
    1.94
     ihre
    1.91
     Their
    1.80
    他们的
    1.79
     ihren
    1.77
    Their
    1.77
     ihrer
    1.77
    Act Density 0.568%

    No Known Activations