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

    Neuronpedia

    INDEX
    Explanations

    academic cheating and dishonesty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     persyaratan
    0.45
    propertyName
    0.41
     प्रतियोग
    0.41
     mock
    0.39
     xổ
    0.39
     psor
    0.39
    kfollowers
    0.38
    selectable
    0.38
     sympathique
    0.38
    mock
    0.38
    POSITIVE LOGITS
     cheating
    0.79
     Cheat
    0.79
     cheat
    0.78
     cheated
    0.74
    Cheat
    0.71
    cheat
    0.68
     cheats
    0.64
    诚信
    0.60
     Chew
    0.59
     Collaboration
    0.57
    Act Density 0.008%

    No Known Activations