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

    Neuronpedia

    INDEX
    Explanations

    Italian place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ల్‌
    0.45
    os
    0.45
     optimised
    0.44
     electrification
    0.42
     мм
    0.42
    стон
    0.42
     perfumes
    0.41
     отвеча
    0.41
    ’.
    0.41
     afterlife
    0.41
    POSITIVE LOGITS
    ഹൃ
    0.46
     控制
    0.46
     التعريف
    0.45
    他在
    0.45
    行为
    0.44
     třeba
    0.44
    വിൽ
    0.44
     DefaultTargets
    0.43
    Reload
    0.42
     qí
    0.41
    Act Density 0.000%

    No Known Activations