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

    Neuronpedia

    INDEX
    Explanations

    i wasn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     입니다
    1.12
    します
    1.09
    합니다
    1.09
    입니다
    1.09
     છે
    1.08
     있습니다
    1.08
     है
    1.07
    られています
    1.01
     हैं
    1.01
    됩니다
    1.00
    POSITIVE LOGITS
     had
    2.64
     hadn
    2.45
     habían
    2.34
     havde
    2.34
     había
    2.32
     hadde
    2.23
    had
    2.12
     hade
    2.08
     was
    2.07
     seemed
    2.06
    Act Density 0.511%

    No Known Activations