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

    Neuronpedia

    INDEX
    Explanations

    mealtimes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lunchtime
    -0.73
     lunch
    -0.68
     Lunch
    -0.65
    Lunch
    -0.60
     breakfast
    -0.60
    lunch
    -0.59
     noon
    -0.59
    morning
    -0.58
    Morning
    -0.58
     luncheon
    -0.57
    POSITIVE LOGITS
    time
    0.84
    脚注の使い方
    0.81
    UnsafeEnabled
    0.60
    TIME
    0.59
     utafitiHapana
    0.59
    rooms
    0.57
    stage
    0.56
    Time
    0.56
    ptonshire
    0.56
    HomeAsUpEnabled
    0.56
    Act Density 0.004%

    No Known Activations