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

    Neuronpedia

    INDEX
    Explanations

    lumin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sexist
    -0.08
    [next
    -0.07
    .sort
    -0.07
    不同的
    -0.06
     whence
    -0.06
    .View
    -0.06
     freak
    -0.06
    ственное
    -0.06
    --;
↵
    -0.06
     grote
    -0.06
    POSITIVE LOGITS
    ُم
    0.08
    ��
    0.07
     lumin
    0.07
    um
    0.07
    agnostics
    0.07
     Lum
    0.07
    UM
    0.07
     Illum
    0.07
    �
    0.07
     lum
    0.07
    Act Density 0.011%

    No Known Activations