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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .<
    -0.07
     vô
    -0.07
    月末
    -0.07
     überh
    -0.06
    .');
↵
    -0.06
     inn
    -0.06
    😻
    -0.06
     confirmed
    -0.06
     morph
    -0.06
    鸣
    -0.06
    POSITIVE LOGITS
    _dept
    0.07
    ضل
    0.07
    -------------
    0.07
    _radio
    0.07
    日本人
    0.07
     Mandela
    0.07
    自如
    0.07
    學
    0.07
    註冊
    0.07
    实验
    0.06
    Act Density 0.008%

    No Known Activations