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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     descom
    1.65
    Buenos
    1.62
    mselves
    1.62
    ج
    1.62
    ición
    1.61
    щем
    1.60
    ре
    1.57
    ीय
    1.57
     rán
    1.56
     gesamten
    1.56
    POSITIVE LOGITS
    𝖾
    2.02
    r
    1.95
    і
    1.92
    هلا
    1.89
    ㄷ
    1.82
     HomePage
    1.79
    ത്വം
    1.78
     CVD
    1.78
     perror
    1.74
    ഡ്
    1.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.