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

    Neuronpedia

    INDEX
    Explanations

    place tickets, countries, or reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.55
    트
    0.47
     село
    0.46
    是我们
    0.46
    ល្អ
    0.46
    Emergency
    0.45
    вига
    0.45
    ла
    0.43
    іль
    0.43
     энер
    0.43
    POSITIVE LOGITS
     Nur
    0.53
     bukan
    0.47
     hubungan
    0.47
    ron
    0.46
     Mus
    0.46
     tanggal
    0.46
     Chop
    0.45
     Ata
    0.45
     blueberry
    0.45
     Bhutan
    0.44
    Act Density 0.000%

    No Known Activations