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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lệnh
    -0.08
    REN
    -0.08
    いただ
    -0.07
    兄
    -0.07
    ��
    -0.07
    enci
    -0.07
    ╗
    -0.07
     تن
    -0.07
    ნ
    -0.07
    сп
    -0.07
    POSITIVE LOGITS
     forgiving
    0.08
     nueva
    0.08
     çalışma
    0.07
    Including
    0.07
     algumas
    0.07
    _yaw
    0.07
    AGING
    0.07
     Nova
    0.06
     ideal
    0.06
     กร
    0.06
    Act Density 0.025%

    No Known Activations