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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ونات
    0.47
    ያንዳ
    0.46
    摫
    0.45
     tambahan
    0.45
    ಞ
    0.44
    عيد
    0.44
     psalm
    0.43
    同时
    0.43
    我现在
    0.42
     подпис
    0.42
    POSITIVE LOGITS
    社
    0.52
    u
    0.47
     ウ
    0.46
    ÉN
    0.45
    e
    0.45
     社
    0.45
     ওয়ে
    0.44
    ્સ
    0.44
     ク
    0.44
    RENGTH
    0.44
    Act Density 0.000%

    No Known Activations