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

    Neuronpedia

    INDEX
    Explanations

    illogical leap, fair across

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     별
    0.45
     btw
    0.45
    별
    0.41
     BTW
    0.39
     모
    0.38
    屢
    0.37
    ខ្លួន
    0.37
    ကြ
    0.34
     relent
    0.34
    ய
    0.34
    POSITIVE LOGITS
    සිය
    0.44
     Excellency
    0.42
    iedy
    0.42
     ehemalige
    0.42
     मुख्यमंत्री
    0.42
    我对
    0.41
     новая
    0.41
     requer
    0.40
     yeni
    0.39
     পরিবর্তে
    0.39
    Act Density 0.000%

    No Known Activations