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

    Neuronpedia

    INDEX
    Explanations

    discount

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Yellow
    -0.07
    昭
    -0.06
     福
    -0.06
    SS
    -0.06
    .tom
    -0.06
     observing
    -0.06
     英
    -0.06
    sand
    -0.06
     strcpy
    -0.06
    民族
    -0.06
    POSITIVE LOGITS
     patio
    0.07
    	exit
    0.07
     Diseases
    0.06
    ými
    0.06
    ↵
↵
↵
    0.06
    ())->
    0.06
     Banner
    0.06
    $sub
    0.06
     errorMsg
    0.06
     comando
    0.06
    Act Density 0.037%

    No Known Activations