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

    Neuronpedia

    INDEX
    Explanations

    time and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tenant
    0.40
    tenant
    0.39
    commonly
    0.38
     commonly
    0.36
     Tenant
    0.36
    াসে
    0.35
     HomeController
    0.35
     tenant
    0.34
    рони
    0.34
     thorns
    0.34
    POSITIVE LOGITS
     minutes
    0.66
     hour
    0.65
     minute
    0.63
     thirty
    0.63
     forty
    0.60
     giờ
    0.59
     minutos
    0.59
     Thirty
    0.59
     часа
    0.58
     минут
    0.57
    Act Density 0.024%

    No Known Activations