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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     deaf
    -0.08
    (GET
    -0.07
    gMaps
    -0.07
     Ö
    -0.07
    ตะ
    -0.06
     강
    -0.06
    Sir
    -0.06
    _namespace
    -0.06
     gentle
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    华
    0.07
     нашей
    0.06
    requ
    0.06
     преп
    0.06
    imization
    0.06
    rotate
    0.06
    REP
    0.06
    ilent
    0.06
     dues
    0.06
    اء
    0.06
    Act Density 0.000%

    No Known Activations