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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    冯
    0.38
    医生
    0.37
     Witch
    0.37
    ęp
    0.37
     Auer
    0.37
    執
    0.37
     أح
    0.36
     intérieur
    0.36
    空间
    0.36
     Coach
    0.36
    POSITIVE LOGITS
     thousand
    0.84
     hundred
    0.82
    thousand
    0.75
    二百
    0.65
    hundred
    0.65
     тыся
    0.64
     ಸಾವಿರ
    0.63
     Hundred
    0.62
    千
    0.61
     Thousand
    0.59
    Act Density 0.102%

    No Known Activations