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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mane
    -0.08
     toplantı
    -0.07
     Vitamin
    -0.07
    (NUM
    -0.07
     topology
    -0.07
    weapons
    -0.07
    竞争
    -0.07
     Toast
    -0.07
    侧面
    -0.06
    (man
    -0.06
    POSITIVE LOGITS
    ouncements
    0.07
    ꡒ
    0.07
    שנתיים
    0.07
     Vancouver
    0.07
    ORED
    0.06
    얔
    0.06
     الصح
    0.06
     gốc
    0.06
     ******************************************************************************/↵
    0.06
    clarations
    0.06
    Act Density 0.016%

    No Known Activations