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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    պ
    0.50
    ია
    0.48
    目光
    0.45
    鍝
    0.45
    ̼
    0.44
     SMAD
    0.43
    Ბ
    0.42
    P
    0.41
    ž
    0.41
    <0x89>
    0.40
    POSITIVE LOGITS
    center
    0.53
    ли
    0.52
     диамет
    0.50
    ground
    0.48
     приветствую
    0.47
    городе
    0.47
    wheat
    0.46
     расходы
    0.45
    регистри
    0.45
     Conoc
    0.45
    Act Density 0.004%

    No Known Activations