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

    Neuronpedia

    INDEX
    Explanations

    messaging apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parker
    0.45
    اد
    0.44
    共产党
    0.41
     витами
    0.41
    cognitive
    0.40
     Corvette
    0.40
    auge
    0.39
     આન
    0.39
    analytic
    0.39
     Cochran
    0.39
    POSITIVE LOGITS
     WhatsApp
    0.91
    WhatsApp
    0.90
     Whatsapp
    0.74
    Telegram
    0.72
     whatsapp
    0.71
     Telegram
    0.70
    Whatsapp
    0.69
    Chats
    0.65
     chats
    0.62
    whatsapp
    0.61
    Act Density 0.021%

    No Known Activations