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

    Neuronpedia

    INDEX
    Explanations

    joining or entering places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    路
    0.39
    ුණ
    0.38
     stored
    0.38
     dissatisfied
    0.38
     surrounding
    0.38
     зага
    0.37
    ُو
    0.37
    上的
    0.37
    幾
    0.37
    داف
    0.36
    POSITIVE LOGITS
     Stand
    0.41
     Reich
    0.41
     bilinear
    0.41
     Crews
    0.40
     Pile
    0.39
     회사
    0.39
     WK
    0.39
    Optionals
    0.39
     질문
    0.38
     Heap
    0.37
    Act Density 0.004%

    No Known Activations