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

    Neuronpedia

    INDEX
    Explanations

    scores and similarities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     البر
    -0.08
     змі
    -0.08
    verket
    -0.08
     الإم
    -0.08
     spars
    -0.08
    šķ
    -0.07
     المتحدة
    -0.07
     الإد
    -0.07
    本道
    -0.07
     remedies
    -0.07
    POSITIVE LOGITS
     ranking
    0.10
     greatness
    0.09
     greed
    0.09
    ranking
    0.09
     scores
    0.09
    排名
    0.09
    -ranking
    0.09
    评分
    0.08
     rankings
    0.08
     >=
    0.08
    Act Density 0.021%

    No Known Activations