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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     contrace
    -0.84
     Ukrain
    -0.80
     externalToEVAOnly
    -0.76
     behavi
    -0.73
     Croat
    -0.68
     Palest
    -0.68
     Ys
    -0.68
    racuse
    -0.66
     guiIcon
    -0.65
     Indones
    -0.65
    POSITIVE LOGITS
     booked
    0.70
     daunting
    0.66
     Badge
    0.64
    ailable
    0.63
     Arche
    0.62
     Review
    0.61
     challenging
    0.60
     progressing
    0.60
     contested
    0.59
    fan
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.