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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     env
    -0.07
    �이
    -0.07
    (face
    -0.07
    还是要
    -0.06
    Scan
    -0.06
     ноя
    -0.06
    数据分析
    -0.06
    енную
    -0.06
     veterinary
    -0.06
    chool
    -0.06
    POSITIVE LOGITS
     Büyük
    0.07
    lez
    0.07
    伟
    0.07
    tam
    0.07
    awi
    0.06
    jected
    0.06
     trolling
    0.06
    론
    0.06
    iflower
    0.06
    钰
    0.06
    Act Density 0.010%

    No Known Activations