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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ὖ
    0.46
     privati
    0.42
    utsche
    0.41
    gu
    0.40
    پا
    0.40
     injective
    0.39
    num
    0.39
    знача
    0.39
    ildir
    0.38
    𝗷
    0.38
    POSITIVE LOGITS
     celebrates
    0.36
     सक्रिय
    0.36
    вань
    0.36
     সক্রিয়
    0.35
    ית
    0.34
    バラ
    0.34
     আবশ্যক
    0.34
     captain
    0.34
    申
    0.34
     stick
    0.33
    Act Density 0.002%

    No Known Activations