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

    Neuronpedia

    INDEX
    Explanations

    designed for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rei
    0.48
    ii
    0.43
    rün
    0.43
    Orb
    0.43
     existen
    0.42
    ᆞ
    0.42
     artist
    0.42
    混凝
    0.42
     rozwiąz
    0.41
     অঙ্গ
    0.41
    POSITIVE LOGITS
    ộm
    0.44
     hampers
    0.41
    엿
    0.41
    peč
    0.41
     agress
    0.41
    verläss
    0.40
     fork
    0.39
     वजन
    0.39
    ريق
    0.39
    ضيع
    0.39
    Act Density 0.001%

    No Known Activations