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

    Neuronpedia

    INDEX
    Explanations

    categories and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ولكن
    -0.07
    .byId
    -0.07
     уник
    -0.06
     chậm
    -0.06
    RTL
    -0.06
     Datagram
    -0.06
     servisi
    -0.06
    상위
    -0.06
     매우
    -0.06
    看见
    -0.06
    POSITIVE LOGITS
    ince
    0.07
    counter
    0.07
    errors
    0.06
    -lasting
    0.06
     convolution
    0.06
     livest
    0.06
    rosse
    0.06
    	fire
    0.06
     admin
    0.06
     fav
    0.06
    Act Density 0.034%

    No Known Activations