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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     phi
    -0.07
     @"\
    -0.07
    love
    -0.07
    SeekBar
    -0.07
    室
    -0.07
     giảng
    -0.06
    areas
    -0.06
     dept
    -0.06
    amba
    -0.06
     blades
    -0.06
    POSITIVE LOGITS
    一套
    0.07
     Regulation
    0.06
     stating
    0.06
     yaw
    0.06
    /raw
    0.06
     tổng
    0.06
     بنفس
    0.06
    ază
    0.06
    /files
    0.06
    攒
    0.06
    Act Density 0.000%

    No Known Activations