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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     limes
    1.57
     lames
    1.38
     comical
    1.34
     vio
    1.34
     spacings
    1.32
     mortals
    1.31
     morphisms
    1.29
    年始
    1.29
     anomalies
    1.25
     dividers
    1.25
    POSITIVE LOGITS
    aal
    1.15
    a
    1.01
    وریت
    0.98
    ați
    0.96
    o
    0.92
    çu
    0.89
    વાનું
    0.88
    shen
    0.88
    mär
    0.85
    asını
    0.85
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.