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

    Neuronpedia

    INDEX
    Explanations

    instead of reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نسبت
    0.39
     यूँ
    0.38
    ulet
    0.36
    琥
    0.35
    ایک
    0.34
    ீன்
    0.34
     जरी
    0.34
     પ્રમા
    0.34
    NOWLED
    0.34
    lblCredits
    0.34
    POSITIVE LOGITS
     reality
    1.52
    実際
    1.50
     actuality
    1.43
    reality
    1.38
     realidad
    1.36
     Reality
    1.31
     বাস্তবে
    1.31
    Reality
    1.27
     réalité
    1.26
     realidade
    1.23
    Act Density 0.021%

    No Known Activations