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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     coin
    0.64
     coins
    0.64
    コイン
    0.59
     Coin
    0.57
    币
    0.56
     monedas
    0.55
    Coins
    0.55
     Coins
    0.54
    幣
    0.53
     सिक्के
    0.52
    POSITIVE LOGITS
     Pob
    0.41
    hle
    0.38
     placements
    0.37
    blocked
    0.37
    bomb
    0.37
    thought
    0.37
    اهده
    0.36
    aport
    0.36
     gate
    0.36
     sit
    0.36
    Act Density 0.000%

    No Known Activations