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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    \}$.
    0.50
    renerg
    0.47
    惊喜
    0.45
    圿
    0.44
    cean
    0.44
     bicarbonate
    0.43
     वायरलेस
    0.43
    􀂾
    0.43
    \}$
    0.42
    🚢
    0.42
    POSITIVE LOGITS
    ,
    0.44
     arbit
    0.43
    0.41
    口
    0.41
     Ly
    0.40
     stagn
    0.40
     axis
    0.39
     leader
    0.38
    Sl
    0.38
     anatomy
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.