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

    Neuronpedia

    INDEX
    Explanations

    Lucas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compares
    -0.07
    、『
    -0.07
     hei
    -0.07
     vět
    -0.06
    -notes
    -0.06
     diff
    -0.06
    136
    -0.06
    iniz
    -0.06
     tallest
    -0.06
    еф
    -0.06
    POSITIVE LOGITS
     Lucas
    0.08
     Luna
    0.07
    ـ
    0.07
     luc
    0.06
     Lucifer
    0.06
     ALSO
    0.06
    .likes
    0.06
    jak
    0.06
    阶
    0.06
    ��
    0.06
    Act Density 0.001%

    No Known Activations