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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tài
    -0.07
     Lithuania
    -0.07
    remember
    -0.07
    (interface
    -0.07
    边境
    -0.07
    rome
    -0.06
    воль
    -0.06
    ילד
    -0.06
    伽
    -0.06
    Rooms
    -0.06
    POSITIVE LOGITS
    	ctrl
    0.07
    態
    0.07
    ﯲ
    0.07
    _crit
    0.07
    𬤊
    0.07
    齉
    0.06
    煽
    0.06
    pectrum
    0.06
    .QRect
    0.06
    媆
    0.06
    Act Density 0.022%

    No Known Activations