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

    Neuronpedia

    INDEX
    Explanations

    weekend or multi-day trips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٦
    0.42
    ış
    0.41
    ८
    0.41
    諺
    0.41
    Luca
    0.41
    ೬
    0.41
    Ȧ
    0.39
    这句话
    0.39
     мес
    0.38
    ϭ
    0.38
    POSITIVE LOGITS
     weekend
    0.75
     Weekend
    0.75
    Weekend
    0.71
    weekend
    0.62
     Wochenende
    0.59
     weekends
    0.57
    两天
    0.53
     getaway
    0.51
    三天
    0.47
    週末
    0.46
    Act Density 0.036%

    No Known Activations