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

    Neuronpedia

    INDEX
    Explanations

    scientific names and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ỳnh
    0.49
    សម្រាប់ការ
    0.38
    streetlight
    0.37
    ongyang
    0.37
    ўным
    0.37
    恤
    0.37
    junit
    0.36
    昀
    0.36
    食べて
    0.36
    ສົ່ງ
    0.36
    POSITIVE LOGITS
     flops
    0.46
    ходит
    0.44
     flop
    0.44
     человека
    0.43
     człowie
    0.42
     Mensch
    0.41
     человеку
    0.41
     godz
    0.41
     Behör
    0.41
    Name
    0.39
    Act Density 0.000%

    No Known Activations