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

    Neuronpedia

    INDEX
    Explanations

    program announcements and formal greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yesterday
    0.52
     policemen
    0.50
    prevent
    0.48
    yester
    0.47
    esterday
    0.47
     ieri
    0.45
    😦
    0.44
     preventive
    0.43
    Yesterday
    0.43
     gestern
    0.43
    POSITIVE LOGITS
     программа
    0.50
     برنامه
    0.47
    lanır
    0.46
     பட்டம்
    0.44
     البرنامج
    0.42
     программу
    0.42
     Program
    0.42
     සම්
    0.41
     هند
    0.41
    琚
    0.41
    Act Density 0.003%

    No Known Activations