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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Bound
    -0.07
     LU
    -0.07
    _TUN
    -0.07
    ₠
    -0.07
     UF
    -0.06
     실
    -0.06
    泖
    -0.06
    医用
    -0.06
     Ginny
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     abort
    0.07
    anco
    0.07
    天空部落
    0.07
     pueda
    0.07
    кан
    0.07
     exploits
    0.07
    ']]['
    0.07
    𝚖
    0.07
     inherently
    0.06
    aye
    0.06
    Act Density 0.011%

    No Known Activations