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

    Neuronpedia

    INDEX
    Explanations

    past tense of "to be"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adalah
    0.51
     দিলাম
    0.50
    gave
    0.49
     হলেন
    0.49
    took
    0.48
    became
    0.47
     became
    0.47
    これは
    0.46
    などは
    0.45
     увидел
    0.44
    POSITIVE LOGITS
     был
    0.82
     была
    0.82
     was
    0.80
    Was
    0.80
     было
    0.79
     Was
    0.74
     были
    0.74
     був
    0.73
     була
    0.70
     היה
    0.70
    Act Density 0.013%

    No Known Activations