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

    Neuronpedia

    INDEX
    Explanations

    begin immediately, timer completes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தஞ்ச
    0.39
     Акча
    0.39
    による
    0.38
     Austral
    0.38
     Сер
    0.38
     profitably
    0.37
    lerdir
    0.37
    と比較
    0.37
    ่อย
    0.36
    ="<?=
    0.36
    POSITIVE LOGITS
    給
    0.41
    CaCl
    0.41
     Jamb
    0.37
    infile
    0.37
     برقرار
    0.37
    মন্ত
    0.37
    运维
    0.37
    密封
    0.36
     maintien
    0.36
    ????
    0.35
    Act Density 0.003%

    No Known Activations