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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knocking
    -0.07
    _M
    -0.07
     prone
    -0.07
     T
    -0.06
    ��
    -0.06
     갈
    -0.06
     Build
    -0.06
     HERE
    -0.06
     masks
    -0.06
     phiếu
    -0.06
    POSITIVE LOGITS
    ...',
    0.06
     Wyoming
    0.06
    iddet
    0.06
    など
    0.06
     geliyor
    0.06
    піон
    0.06
    �
    0.06
    兴
    0.06
     stepper
    0.06
    olidays
    0.06
    Act Density 0.011%

    No Known Activations