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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     progressing
    -0.07
    忽然
    -0.07
     graf
    -0.07
    .before
    -0.06
    更
    -0.06
     adapté
    -0.06
    终
    -0.06
    更适合
    -0.06
    prowadzi
    -0.06
     molt
    -0.06
    POSITIVE LOGITS
    ROUTE
    0.08
    :inline
    0.07
     Phillies
    0.07
    ubah
    0.07
    /helper
    0.07
    ﮑ
    0.06
    ffff
    0.06
     ****************************************
    0.06
    一门
    0.06
    _registration
    0.06
    Act Density 0.001%

    No Known Activations