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

    Neuronpedia

    INDEX
    Explanations

    creating code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isomeric
    0.47
     imputed
    0.42
     empir
    0.41
     hydrates
    0.41
    getStringExtra
    0.41
     algoritmo
    0.41
     krwi
    0.40
     enzimas
    0.40
     regulación
    0.39
    DAMAGE
    0.39
    POSITIVE LOGITS
    创建一个
    0.68
     创建
    0.66
     созда
    0.65
    创建
    0.64
    を作成
    0.63
     создавать
    0.59
     create
    0.58
     tạo
    0.57
    สร้าง
    0.55
     created
    0.54
    Act Density 0.082%

    No Known Activations