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

    Neuronpedia

    INDEX
    Explanations

    {@

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (symbol
    -0.08
     startDate
    -0.07
    ۴
    -0.07
    遣
    -0.07
    +'/'+
    -0.07
     trùng
    -0.07
     AREA
    -0.06
     ecl
    -0.06
    CHIP
    -0.06
    ۱۸
    -0.06
    POSITIVE LOGITS
     {@
    0.09
     rst
    0.07
    ):
↵
↵
    0.07
     cash
    0.06
    _container
    0.06
    DNS
    0.06
    дав
    0.06
    ující
    0.06
    지노
    0.06
    persistent
    0.06
    Act Density 0.001%

    No Known Activations