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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     vrste
    0.63
     Среди
    0.61
    er
    0.60
    erade
    0.60
     Republike
    0.60
    ו
    0.59
     lluv
    0.59
    ).}
    0.58
     daarmee
    0.57
    tedir
    0.57
    POSITIVE LOGITS
    لا
    0.75
    ف
    0.74
    فن
    0.66
    ات
    0.65
    پ
    0.64
    箜
    0.64
    सो
    0.64
    أ
    0.64
    अ
    0.63
    را
    0.62
    Act Density 2.823%

    No Known Activations