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

    Neuronpedia

    INDEX
    Explanations

    create object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    門
    0.43
    璈
    0.41
    இய
    0.41
    setRoi
    0.41
    بین
    0.40
    垡
    0.39
    喱
    0.39
    筫
    0.39
     مراسم
    0.39
    部位
    0.39
    POSITIVE LOGITS
     Creator
    0.42
     созда
    0.40
     creates
    0.39
     creator
    0.39
     Activ
    0.39
     MongoClient
    0.39
     Tạo
    0.39
     terci
    0.38
    ospod
    0.38
     stepfather
    0.38
    Act Density 0.005%

    No Known Activations