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
     scholarships
    -0.07
     abusive
    -0.07
    丰田
    -0.07
    为导向
    -0.07
     дорог
    -0.07
    样子
    -0.07
    提到
    -0.07
     Being
    -0.07
    "]))
    -0.06
    สงบ
    -0.06
    POSITIVE LOGITS
    про
    0.07
     יודעים
    0.07
     המח
    0.07
    кр
    0.06
    웢
    0.06
    贪
    0.06
    Mine
    0.06
    ��
    0.06
    حا
    0.06
     gains
    0.06
    Act Density 0.025%

    No Known Activations