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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лише
    -0.07
     warmed
    -0.07
     götür
    -0.07
    -service
    -0.07
    喝
    -0.07
     detectors
    -0.07
     соз
    -0.07
    ляем
    -0.06
    小姐
    -0.06
    enerated
    -0.06
    POSITIVE LOGITS
     Kamp
    0.07
     Anders
    0.07
    	        ↵
    0.07
     Baron
    0.07
    도
    0.06
    0.06
    　　 　 　
    0.06
    　　 　
    0.06
    pers
    0.06
    ,n
    0.06
    Act Density 0.014%

    No Known Activations