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

    Neuronpedia

    INDEX
    Explanations

    subject wasn't or hadn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    後來
    0.47
    觀察
    0.46
    ovaniyu
    0.45
    練習
    0.42
     उसको
    0.42
     후에
    0.42
    了一下
    0.42
    సారి
    0.42
    詢
    0.41
     highlighting
    0.40
    POSITIVE LOGITS
     esche
    0.54
     wasn
    0.44
     spraw
    0.44
     seldom
    0.42
     ceas
    0.41
     cuyo
    0.41
     sprawl
    0.41
     भले
    0.40
     बेशक
    0.40
     rarely
    0.40
    Act Density 0.009%

    No Known Activations