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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hur
    0.60
     assumes
    0.55
     malls
    0.53
     Hur
    0.53
     mums
    0.52
     hurricanes
    0.52
     instruções
    0.52
     acreditar
    0.52
     Winchester
    0.51
     Romney
    0.50
    POSITIVE LOGITS
    انب
    0.73
    ק
    0.57
    en
    0.56
    لام
    0.55
    انية
    0.54
    ราว
    0.54
    س
    0.53
    危険
    0.52
     Syndicate
    0.52
    لي
    0.52
    Act Density 0.000%

    No Known Activations