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

    Neuronpedia

    INDEX
    Explanations

    cheating and unfair advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.09
    ल
    1.03
    स
    1.01
    ی
    0.99
    ش
    0.92
    ન
    0.92
    اء
    0.91
    و
    0.91
    ड
    0.89
    </h2>
    0.89
    POSITIVE LOGITS
     cheating
    1.24
     cheated
    1.22
     Cheat
    1.02
    ení
    0.99
     cheats
    0.98
     cheat
    0.94
    ية
    0.84
     органов
    0.84
    រយៈ
    0.84
     роста
    0.82
    Act Density 0.008%

    No Known Activations