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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ç·
    -0.80
    NEWS
    -0.70
     Neigh
    -0.68
    IA
    -0.68
     USPS
    -0.68
     Neighbor
    -0.67
     Neighborhood
    -0.67
     RN
    -0.64
     Disapp
    -0.64
     Berks
    -0.63
    POSITIVE LOGITS
    know
    0.82
    arah
    0.78
    adr
    0.72
    tem
    0.72
    oops
    0.70
    endi
    0.70
    rounded
    0.68
    inters
    0.67
    ulum
    0.66
     Ancients
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.