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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    饲养
    -0.08
     bounding
    -0.08
    DISABLE
    -0.07
    EMPTY
    -0.07
    amus
    -0.07
    Initialize
    -0.07
     Hank
    -0.07
    羊肉
    -0.07
    mqtt
    -0.07
    flags
    -0.07
    POSITIVE LOGITS
    ᴀ
    0.07
     fellow
    0.06
     Lo
    0.06
    ceipt
    0.06
     Verg
    0.06
    rike
    0.06
     Persistent
    0.06
    理工
    0.06
     Weiner
    0.06
    Sci
    0.06
    Act Density 0.250%

    No Known Activations