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

    Neuronpedia

    INDEX
    Explanations

    court numbers and ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FIVE
    -0.87
    สอง
    -0.86
     TWO
    -0.86
     five
    -0.85
    THIRD
    -0.81
     inilah
    -0.79
     چهارم
    -0.77
     картофе
    -0.76
     չ
    -0.76
     two
    -0.75
    POSITIVE LOGITS
     seventy
    1.55
     Seventy
    1.55
     seventeenth
    1.53
     Sixty
    1.52
     eighty
    1.51
     eighteenth
    1.47
     fourteenth
    1.46
     sixty
    1.42
     sixteenth
    1.42
     Eighty
    1.39
    Act Density 0.109%

    No Known Activations