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

    Neuronpedia

    INDEX
    Explanations

    daily happenings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     months
    -1.13
     ダイヤ
    -1.02
    months
    -0.98
    winter
    -0.96
    🈁
    -0.94
     WINTER
    -0.93
    ाला
    -0.92
    ♗
    -0.92
    outez
    -0.92
    jahr
    -0.92
    POSITIVE LOGITS
     daily
    2.19
     day
    2.13
     tomorrow
    1.84
     today
    1.77
     hôm
    1.70
     yesterday
    1.62
    Daily
    1.61
     Daily
    1.59
    daily
    1.59
     morning
    1.55
    Act Density 0.128%

    No Known Activations