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

    Neuronpedia

    INDEX
    Explanations

    numbered days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.68
    Trim
    0.60
     equalize
    0.57
     minimize
    0.57
    Ка
    0.57
     allons
    0.56
     halftime
    0.56
     formulate
    0.54
    सँग
    0.54
     Snoop
    0.54
    POSITIVE LOGITS
    day
    0.92
     päev
    0.88
     day
    0.87
     giornata
    0.85
    一日
    0.84
     день
    0.83
     दिन
    0.82
     dzień
    0.75
     DAY
    0.74
     diurnal
    0.74
    Act Density 0.128%

    No Known Activations