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

    Neuronpedia

    INDEX
    Explanations

    listing descriptors with and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    પુર
    0.39
     dass
    0.38
     dispon
    0.37
     dictators
    0.34
     others
    0.34
     sust
    0.34
     zug
    0.34
     subdue
    0.33
     bahwa
    0.33
     altres
    0.33
    POSITIVE LOGITS
    င
    0.45
    ธุรก
    0.41
    orderHint
    0.40
    䢎
    0.40
     ইন্টারনেট
    0.39
    ник
    0.39
    樯
    0.39
     επιχει
    0.39
    internet
    0.38
     Riding
    0.38
    Act Density 0.001%

    No Known Activations