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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ع
    0.66
    ల్
    0.57
    για
    0.56
    ル
    0.55
    Evidence
    0.52
     Evidence
    0.51
    dwelling
    0.51
    ร์
    0.51
    ական
    0.50
    ء
    0.50
    POSITIVE LOGITS
     statesman
    0.67
     statesmen
    0.63
     со
    0.62
    நபியே
    0.62
     аккумуля
    0.61
     acceptors
    0.59
    িষ্ট
    0.58
     asam
    0.57
     Sino
    0.57
    Ս
    0.57
    Act Density 0.166%

    No Known Activations