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

    Neuronpedia

    INDEX
    Explanations

    document formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _exist
    -0.07
    #{
    -0.07
    _Red
    -0.07
    enchmark
    -0.06
    .sender
    -0.06
    .dead
    -0.06
    ejs
    -0.06
    .car
    -0.06
     í
    -0.06
     HC
    -0.06
    POSITIVE LOGITS
    40
    0.07
     Non
    0.06
     всё
    0.06
     وت
    0.06
     đang
    0.06
     شرق
    0.06
     luôn
    0.06
    ��
    0.06
    由
    0.06
     작업
    0.06
    Act Density 0.012%

    No Known Activations