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

    Neuronpedia

    INDEX
    Explanations

    ut

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inspace
    -0.07
    行业
    -0.07
    ocese
    -0.06
    пример
    -0.06
     embraces
    -0.06
    -flag
    -0.06
    γκό
    -0.06
     نشده
    -0.06
    Gün
    -0.06
    =""></
    -0.06
    POSITIVE LOGITS
     those
    0.07
     Athena
    0.07
     Those
    0.06
     cheer
    0.06
    Those
    0.06
    utes
    0.06
     falsehood
    0.06
    /Page
    0.06
     cùng
    0.06
     становить
    0.06
    Act Density 0.001%

    No Known Activations