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

    Neuronpedia

    INDEX
    Explanations

    Comparing situations, hardship, gratitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    南宋
    -0.07
    .InnerException
    -0.07
     no
    -0.07
    星级酒店
    -0.06
    �
    -0.06
    纤
    -0.06
    enor
    -0.06
    習慣
    -0.06
    让人
    -0.06
    نهار
    -0.06
    POSITIVE LOGITS
    ienza
    0.07
    这三个
    0.07
    清净
    0.07
    -picture
    0.07
    젝
    0.07
     Rising
    0.07
    =q
    0.06
    清
    0.06
    tır
    0.06
    위원회
    0.06
    Act Density 0.039%

    No Known Activations