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

    Neuronpedia

    INDEX
    Explanations

    Reference materials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pauses
    -0.06
    Yaw
    -0.06
     Blackburn
    -0.06
     fluent
    -0.06
    ि,
    -0.06
    	help
    -0.06
     đặt
    -0.06
    _PICTURE
    -0.06
    _UART
    -0.06
    аб
    -0.06
    POSITIVE LOGITS
    ,args
    0.07
     AF
    0.06
     escap
    0.06
     Đặc
    0.06
     رع
    0.06
     mau
    0.06
     групп
    0.06
    InnerHTML
    0.06
     Erk
    0.06
     rampage
    0.06
    Act Density 0.072%

    No Known Activations