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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peur
    -0.08
    Clone
    -0.08
    Filters
    -0.08
     clon
    -0.08
    分钱
    -0.08
     cloning
    -0.08
    .filters
    -0.08
     freel
    -0.08
     toxin
    -0.08
     phân
    -0.08
    POSITIVE LOGITS
     ملاقات
    0.11
     speeches
    0.10
    习近平
    0.10
     زيارة
    0.09
    外交
    0.09
     Reuters
    0.09
     rhetoric
    0.09
     briefing
    0.09
     Putin
    0.09
     సమావేశ
    0.09
    Act Density 0.120%

    No Known Activations