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

    Neuronpedia

    INDEX
    Explanations

    emotions and personal reflections related to regret and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "day" or "face"

    np_acts-logits-general · gemini-2.0-flash

    daily reminders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estimés
    -0.67
    脚注の使い方
    -0.55
     الحره
    -0.51
    CodeAttribute
    -0.50
     оригіналу
    -0.49
     Schnell
    -0.49
    alised
    -0.48
    yolo
    -0.47
    WithMany
    -0.47
    glBind
    -0.46
    POSITIVE LOGITS
     daily
    0.92
     reminders
    0.89
     dagelijks
    0.89
     reminder
    0.81
     daglig
    0.80
    daily
    0.79
    每天
    0.78
     diariamente
    0.75
     ежедневно
    0.74
    reminder
    0.73
    Act Density 0.208%

    No Known Activations