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

    Neuronpedia

    INDEX
    Explanations

    like a / as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lediglich
    0.46
     called
    0.45
     dénom
    0.45
     específico
    0.44
     sogenannten
    0.44
     gọi
    0.43
    碜
    0.43
     kerül
    0.42
     demeure
    0.41
    罅
    0.41
    POSITIVE LOGITS
    まるで
    0.67
     마치
    0.63
    正常
    0.54
     professionals
    0.47
     정상
    0.46
    真正的
    0.46
     behaved
    0.45
     profesionales
    0.44
     behaves
    0.43
     savages
    0.43
    Act Density 0.108%

    No Known Activations