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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stead
    -0.06
     slugg
    -0.06
     Sne
    -0.06
     суд
    -0.06
     hơn
    -0.06
    asel
    -0.06
    iker
    -0.06
    '>↵
    -0.06
     nowhere
    -0.06
     виде
    -0.06
    POSITIVE LOGITS
    LB
    0.08
    大雨
    0.08
    인터넷
    0.07
    僰
    0.07
    _fs
    0.07
    targets
    0.07
     layoffs
    0.07
    观众
    0.07
     accelerated
    0.07
     الغربية
    0.07
    Act Density 0.016%

    No Known Activations