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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Mahjong
    -0.76
     VIDEOS
    -0.75
    à¼
    -0.68
    VERTIS
    -0.66
    VERTISEMENT
    -0.66
    ilts
    -0.66
    arov
    -0.66
    Coun
    -0.66
    andel
    -0.66
    ropolitan
    -0.64
    POSITIVE LOGITS
    lust
    0.85
    hammer
    0.78
    slow
    0.76
     apex
    0.72
    stead
    0.69
     heartbeat
    0.69
     superpower
    0.68
    guard
    0.67
    wallet
    0.67
    shirt
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.