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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ColumnsMode
    -0.08
     valuable
    -0.08
    孕育
    -0.07
     GENERATED
    -0.07
     UIScreen
    -0.07
     %@",
    -0.07
    奇怪
    -0.07
    덟
    -0.07
     Deadly
    -0.06
    رتبط
    -0.06
    POSITIVE LOGITS
    vale
    0.08
     ق
    0.07
    .Collection
    0.07
    荆
    0.07
    dup
    0.06
     witch
    0.06
     United
    0.06
    优化
    0.06
     cli
    0.06
     ++↵
    0.06
    Act Density 0.045%

    No Known Activations