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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ishop
    -0.07
     Tran
    -0.07
    بريد
    -0.07
     nominate
    -0.06
     TXT
    -0.06
     Pradesh
    -0.06
    .Center
    -0.06
    �
    -0.06
    produce
    -0.06
     geme
    -0.06
    POSITIVE LOGITS
    燹
    0.07
    澽
    0.07
    ↛
    0.07
    름
    0.06
    _refs
    0.06
    "/
    0.06
    輛
    0.06
    _HANDLER
    0.06
    被盗
    0.06
     Metal
    0.06
    Act Density 0.218%

    No Known Activations