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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cricket
    -0.07
     Senators
    -0.07
    croft
    -0.07
    となった
    -0.06
    Lie
    -0.06
    enh
    -0.06
    葭
    -0.06
    举行了
    -0.06
    房
    -0.06
     gee
    -0.06
    POSITIVE LOGITS
     נהנ
    0.07
     XCTest
    0.07
    흘
    0.07
     artyku
    0.07
    .bl
    0.07
    עבוד
    0.07
    .bel
    0.07
    ||||
    0.07
    [cnt
    0.07
    亳
    0.07
    Act Density 0.035%

    No Known Activations