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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Play
    -0.07
    Shoot
    -0.07
    果汁
    -0.07
    然
    -0.07
    Snow
    -0.07
    지고
    -0.07
     cooking
    -0.07
    打入
    -0.06
    MON
    -0.06
     chalk
    -0.06
    POSITIVE LOGITS
     datatype
    0.08
     bath
    0.08
    твержден
    0.07
    sig
    0.07
    ⚣
    0.07
     partnership
    0.07
    🇳
    0.07
    댜
    0.07
     каталог
    0.07
    _gid
    0.06
    Act Density 0.005%

    No Known Activations