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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nil
    0.65
    ലെസ്
    0.63
     PI
    0.59
     WIRE
    0.59
     '')
    0.58
     ká
    0.57
     Bellevue
    0.57
    Fatal
    0.56
    Tan
    0.56
     Petersburg
    0.56
    POSITIVE LOGITS
    君
    0.61
    सुद्धा
    0.58
     ಕಿ
    0.55
    的高度
    0.55
    🏡
    0.54
     مره
    0.54
    ictionnaire
    0.53
     Theorems
    0.53
     fireplaces
    0.52
    reshold
    0.52
    Act Density 0.000%

    No Known Activations