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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    fire
    -0.71
    iod
    -0.65
     poisoned
    -0.63
    Football
    -0.62
     adversely
    -0.61
    ished
    -0.61
     deflation
    -0.61
     fallout
    -0.60
     volleyball
    -0.60
     unravel
    -0.60
    POSITIVE LOGITS
     Lynd
    0.82
     Strongh
    0.79
     Dumb
    0.79
     {\
    0.74
     Larson
    0.72
     Bark
    0.70
    Gro
    0.69
     Glas
    0.69
     Outer
    0.69
    âķIJ
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.