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

    Neuronpedia

    INDEX
    Explanations

    numbers 1 and 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eighty
    0.73
     seventy
    0.67
    四十
    0.67
     चालीस
    0.65
     চল্লিশ
    0.61
     Eighty
    0.60
    Forty
    0.59
     ৭৫
    0.59
     sixty
    0.59
    三十
    0.59
    POSITIVE LOGITS
     two
    1.16
     ১
    1.04
     δύο
    1.02
     दो
    0.98
     one
    0.97
     TWO
    0.97
     १
    0.96
     zwei
    0.94
     deux
    0.93
    two
    0.91
    Act Density 0.142%

    No Known Activations