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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     අය
    0.42
     Dishes
    0.40
     ওয়ার্ড
    0.40
     अल्ट्रा
    0.40
    ന്നും
    0.39
    Задача
    0.39
    ित्य
    0.39
    ায়ার
    0.38
     இந்த
    0.38
     insulted
    0.38
    POSITIVE LOGITS
    dagen
    0.36
    osław
    0.36
    提高
    0.35
     документи
    0.35
    Raise
    0.35
    tai
    0.34
     sym
    0.34
     Raise
    0.34
     lem
    0.33
    થ
    0.33
    Act Density 0.000%

    No Known Activations