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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     tố
    -0.07
    HEN
    -0.07
     Dion
    -0.06
    吟
    -0.06
     Jacqueline
    -0.06
    谓
    -0.06
    IRECT
    -0.06
    parent
    -0.06
    すべて
    -0.06
    reasonable
    -0.06
    POSITIVE LOGITS
    ȼ
    0.08
     Belgi
    0.07
     politic
    0.07
    ואי
    0.07
     mirac
    0.07
    ześ
    0.07
    =value
    0.07
     miss
    0.07
    CLK
    0.07
    (local
    0.07
    Act Density 0.022%

    No Known Activations