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

    Neuronpedia

    INDEX
    Explanations

    therefore or so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     świecie
    0.27
     eftersom
    0.25
     أو
    0.25
     árabe
    0.24
     aldı
    0.23
     चूंकि
    0.23
     定义
    0.23
    をし
    0.23
     médian
    0.23
     protezione
    0.22
    POSITIVE LOGITS
     it
    0.42
    it
    0.30
     It
    0.28
    It
    0.28
    you
    0.28
     can
    0.27
    oth
    0.27
     they
    0.26
    oner
    0.26
    มัน
    0.26
    Act Density 0.223%

    No Known Activations