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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _INT
    -0.07
     wandering
    -0.07
    延长
    -0.07
     fuera
    -0.07
     Cowboy
    -0.07
    청소
    -0.07
    杭州
    -0.06
     בב
    -0.06
     Nhiều
    -0.06
    .nl
    -0.06
    POSITIVE LOGITS
    thumbnails
    0.07
     обрат
    0.07
    imulator
    0.07
    uslim
    0.07
     projection
    0.07
    apon
    0.07
     Flavor
    0.07
    🌞
    0.07
     safety
    0.06
     Horm
    0.06
    Act Density 0.007%

    No Known Activations