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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _q
    -0.08
     Boat
    -0.07
    gear
    -0.06
    瞩
    -0.06
    Assets
    -0.06
    _ROUTE
    -0.06
    旗下
    -0.06
    Receive
    -0.06
    道教
    -0.06
     mol
    -0.06
    POSITIVE LOGITS
     Ed
    0.07
    新政
    0.07
    oppel
    0.07
    ุง
    0.07
     ime
    0.06
    셈
    0.06
    [w
    0.06
    很难
    0.06
    \Bridge
    0.06
    serialized
    0.06
    Act Density 0.009%

    No Known Activations