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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ew
    0.52
    Operator
    0.47
    لاف
    0.46
     často
    0.44
    航空公司
    0.44
    VIOUS
    0.44
    ោធ
    0.44
     différences
    0.43
     fenomeno
    0.43
    GaussianBlur
    0.42
    POSITIVE LOGITS
    oriented
    0.52
    town
    0.48
    한다는
    0.46
    take
    0.46
    running
    0.46
    os
    0.46
     karat
    0.44
    captive
    0.44
    stone
    0.43
    ze
    0.43
    Act Density 0.001%

    No Known Activations