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

    Neuronpedia

    INDEX
    Explanations

    evening activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lunch
    0.79
     lunch
    0.78
    上午
    0.73
    Lunch
    0.71
     lunches
    0.71
    ランチ
    0.70
     lunchtime
    0.70
    中午
    0.70
     pranzo
    0.68
    lunch
    0.67
    POSITIVE LOGITS
     night
    1.68
     tonight
    1.63
     nightly
    1.59
     nighttime
    1.58
     nocturnal
    1.58
    Night
    1.56
     Night
    1.52
     Tonight
    1.50
    Tonight
    1.49
    night
    1.43
    Act Density 0.126%

    No Known Activations