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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     colonial
    -0.08
    Gui
    -0.07
    igua
    -0.07
    重要な
    -0.07
     judicial
    -0.07
     encountered
    -0.07
     воды
    -0.07
    舶
    -0.07
    romo
    -0.07
     metros
    -0.07
    POSITIVE LOGITS
    한다면
    0.07
    تقار
    0.07
    이는
    0.06
    �
    0.06
     nieruch
    0.06
    /';↵↵
    0.06
    人类
    0.06
    分彩
    0.06
    RAND
    0.06
     З
    0.06
    Act Density 0.003%

    No Known Activations