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

    Neuronpedia

    INDEX
    Explanations

    time formats with colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JM
    0.71
     प्रणाम
    0.71
     riconosc
    0.66
     জ্বল
    0.65
     Reagan
    0.65
     Franklin
    0.65
     Doubt
    0.64
    yse
    0.61
    ب
    0.59
    جست
    0.59
    POSITIVE LOGITS
     hours
    0.89
     horas
    0.87
     madrugada
    0.84
     early
    0.83
    Hours
    0.83
     Hours
    0.81
     ساعات
    0.79
     hourly
    0.78
     Early
    0.77
     hour
    0.77
    Act Density 0.076%

    No Known Activations