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

    Neuronpedia

    INDEX
    Explanations

    not perfectly/exactly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zarówno
    0.51
     zowel
    0.50
     nejen
    0.49
    不管是
    0.48
    不錯
    0.47
     sowohl
    0.46
    无论是
    0.45
     গুরুত্বপূর্ণ
    0.42
     تقريبا
    0.41
    几乎
    0.40
    POSITIVE LOGITS
     necessarily
    1.15
     necessariamente
    1.02
     necesariamente
    1.01
    完全に
    1.00
    完全
    0.98
     completely
    0.96
     exactly
    0.94
     teljesen
    0.94
     sepenuhnya
    0.94
     полностью
    0.93
    Act Density 0.258%

    No Known Activations