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

    Neuronpedia

    INDEX
    Explanations

    Citations in scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swing
    -0.07
     Vancouver
    -0.06
     repetition
    -0.06
     Flavor
    -0.06
     me
    -0.06
     Capacity
    -0.06
     occupancy
    -0.06
    	HANDLE
    -0.06
     homosexuality
    -0.06
    Cam
    -0.06
    POSITIVE LOGITS
     กล
    0.07
    ...">↵
    0.06
    BOOK
    0.06
    .serializer
    0.06
    oplast
    0.06
    urgeon
    0.06
    uridad
    0.06
    toList
    0.06
    ์การ
    0.06
    ＝
    0.06
    Act Density 0.012%

    No Known Activations