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

    Neuronpedia

    INDEX
    Explanations

    one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ayrıca
    0.73
    সমস্ত
    0.70
     außerdem
    0.70
    ృత
    0.68
    また
    0.65
    undaki
    0.64
    elum
    0.64
     পরিমাণ
    0.64
     két
    0.63
    heten
    0.63
    POSITIVE LOGITS
     ones
    4.86
     one
    3.57
     Ones
    3.26
    ones
    2.97
     celui
    2.51
     unul
    2.50
    one
    2.49
     하나
    2.40
     یکی
    2.35
     واحدة
    2.34
    Act Density 0.657%

    No Known Activations