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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    产品
    0.56
    кро
    0.55
    нда
    0.51
    product
    0.50
    پ
    0.50
    ที
    0.50
    плю
    0.50
    我
    0.50
    普通的
    0.49
    expressions
    0.49
    POSITIVE LOGITS
     karate
    0.61
     Hacienda
    0.57
     systems
    0.56
    Wiki
    0.56
     若
    0.56
     piazza
    0.56
     rampage
    0.55
     reimag
    0.55
     vacation
    0.53
     Villages
    0.53
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.