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

    Neuronpedia

    INDEX
    Explanations

    specific entities languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Advice
    0.72
    Sur
    0.70
     Ako
    0.69
    شارات
    0.67
    림
    0.67
     হস্ত
    0.65
    fels
    0.65
     prevails
    0.63
    狙
    0.62
     মৌসুম
    0.62
    POSITIVE LOGITS
    hect
    0.72
    тріш
    0.65
     Cantor
    0.65
    𝙾
    0.65
     मंत्रियों
    0.64
     بالٹ
    0.64
     odit
    0.63
     Бре
    0.62
     મૂળ
    0.62
     konflik
    0.61
    Act Density 0.044%

    No Known Activations