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

    Neuronpedia

    INDEX
    Explanations

    performs much better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     für
    0.50
    เพื่อ
    0.50
     یک
    0.48
     для
    0.47
    帮
    0.47
     redis
    0.47
    性别
    0.46
    สำหรับ
    0.45
    另一个
    0.45
     (
    0.44
    POSITIVE LOGITS
     forêts
    0.48
    보다는
    0.45
     atthakath
    0.44
     ماشینونه
    0.43
     densément
    0.42
     energi
    0.42
     hormati
    0.42
     energije
    0.41
    <unused21>
    0.41
     ماين
    0.41
    Act Density 0.002%

    No Known Activations