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

    Neuronpedia

    INDEX
    Explanations

    kingdoms and rulers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    恶意
    0.49
     будет
    0.41
     ধ্যান
    0.39
     می‌تواند
    0.38
     হয়ে
    0.38
     Qxg
    0.38
    博士
    0.38
     художник
    0.37
    untary
    0.37
     slippery
    0.37
    POSITIVE LOGITS
     islands
    0.48
     peuple
    0.48
     resett
    0.48
     ಆನಿ
    0.47
    citizens
    0.47
    instit
    0.46
     pemerintah
    0.46
     isla
    0.46
    city
    0.45
    社の
    0.44
    Act Density 0.191%

    No Known Activations