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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts followed by 'of'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puede
    0.55
     может
    0.51
     можна
    0.50
    Cuando
    0.50
    لك
    0.49
     podem
    0.49
     можно
    0.48
     חלק
    0.48
     peuvent
    0.47
     כאשר
    0.47
    POSITIVE LOGITS
     of
    0.93
     ofthe
    0.83
    ของการ
    0.76
    នៃ
    0.73
     της
    0.65
     của
    0.63
     thereof
    0.63
     ofx
    0.61
    의
    0.60
    នៃការ
    0.58
    Act Density 1.195%

    No Known Activations