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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (vol
    -0.07
    /*↵
    -0.07
     /\.(
    -0.06
    (prod
    -0.06
     ↵        ↵
    -0.06
    tn
    -0.06
    instein
    -0.06
    祐
    -0.06
    owers
    -0.06
    来临
    -0.06
    POSITIVE LOGITS
     messages
    0.09
     showMessage
    0.09
     message
    0.08
    长辈
    0.07
     LPARAM
    0.07
     the
    0.07
    ⇢
    0.07
    ResourceManager
    0.07
    _request
    0.07
     messaging
    0.07
    Act Density 0.053%

    No Known Activations