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

    Neuronpedia

    INDEX
    Explanations

    just wanted to send a reminder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getting
    0.61
    ொண்டு
    0.60
    インスト
    0.57
     decidir
    0.56
     deciding
    0.55
     especialistas
    0.55
     mathrm
    0.55
    وون
    0.54
     decidiu
    0.54
     baad
    0.53
    POSITIVE LOGITS
     reminder
    0.84
     Reminder
    0.79
    Reminder
    0.79
     remind
    0.74
    提醒
    0.73
    reminder
    0.69
     reminders
    0.66
     напом
    0.65
     напомина
    0.65
     reiterate
    0.64
    Act Density 0.076%

    No Known Activations