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

    Neuronpedia

    INDEX
    Explanations

    AI model training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elli
    -0.07
    人员
    -0.07
    庆
    -0.06
     Мы
    -0.06
    	typedef
    -0.06
    оты
    -0.06
     datatype
    -0.06
    tbl
    -0.06
    dismiss
    -0.06
     Robert
    -0.06
    POSITIVE LOGITS
    表示
    0.07
    VERTISEMENT
    0.07
     playwright
    0.06
     ange
    0.06
     useful
    0.06
    _Api
    0.06
     interfere
    0.06
     takdir
    0.06
     возрасте
    0.06
    fullname
    0.06
    Act Density 0.047%

    No Known Activations