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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    they
    -0.07
     sare
    -0.07
     nasal
    -0.07
    дается
    -0.07
    �
    -0.07
     سبح
    -0.07
    (ch
    -0.07
    毕业
    -0.07
    �
    -0.07
    ecture
    -0.06
    POSITIVE LOGITS
    ologie
    0.07
    ˯
    0.07
    ߖ
    0.07
    岣
    0.07
    �
    0.06
    摁
    0.06
    Ղ
    0.06
    髅
    0.06
     ')[
    0.06
    꼰
    0.06
    Act Density 0.000%

    No Known Activations