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

    Neuronpedia

    INDEX
    Explanations

    end of year dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     starting
    0.83
    ตั้งแต่
    0.78
     freshman
    0.78
     startup
    0.76
     Starting
    0.74
     начина
    0.74
     bracing
    0.73
     freshmen
    0.72
     desde
    0.72
    Starting
    0.70
    POSITIVE LOGITS
    结束
    1.31
     окончания
    1.10
    終
    1.09
     پایان
    1.08
     koniec
    1.07
    终止
    1.06
    結束
    1.02
     selesai
    1.01
    End
    0.99
    Termination
    0.99
    Act Density 0.459%

    No Known Activations