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

    Neuronpedia

    INDEX
    Explanations

    common conjunctions and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doctorate
    0.44
     及
    0.43
     long
    0.42
     及び
    0.41
     slew
    0.39
     ainfi
    0.39
     nostru
    0.39
     nurse
    0.38
     تاسو
    0.38
     vaccine
    0.38
    POSITIVE LOGITS
    the
    0.77
    The
    0.74
    의
    0.64
     the
    0.61
     את
    0.61
    它的
    0.59
    的价格
    0.56
    THE
    0.54
     thei
    0.54
    을
    0.54
    Act Density 0.078%

    No Known Activations