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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ritical
    -0.71
    URI
    -0.69
    psc
    -0.68
    RI
    -0.67
    ItemTracker
    -0.67
    lli
    -0.66
    prus
    -0.66
    ntil
    -0.65
    SHIP
    -0.64
    rique
    -0.63
    POSITIVE LOGITS
     sights
    0.77
     fuse
    0.70
     Edison
    0.68
     Yosemite
    0.67
    Nap
    0.64
     arrow
    0.62
     Nap
    0.61
    wall
    0.60
     Apprentice
    0.59
     Mt
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.