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

    Neuronpedia

    INDEX
    Explanations

    winning and satisfaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Olymp
    -0.07
    щий
    -0.07
    -scroll
    -0.06
     slid
    -0.06
    Grid
    -0.06
     uncertain
    -0.06
     Easy
    -0.06
     approach
    -0.06
    Early
    -0.06
    ootball
    -0.06
    POSITIVE LOGITS
     配
    0.06
    	ERROR
    0.06
    .Acc
    0.06
     getCategory
    0.06
     trái
    0.06
    �
    0.06
     compat
    0.06
     AF
    0.06
    博士
    0.06
     Next
    0.06
    Act Density 0.107%

    No Known Activations