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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    찜
    -0.08
    מפורט
    -0.08
    膊
    -0.08
    桫
    -0.07
    _TODO
    -0.07
     Cuisine
    -0.07
    溞
    -0.07
    农贸市场
    -0.07
    px
    -0.07
    חיבור
    -0.07
    POSITIVE LOGITS
     scholarly
    0.07
    -container
    0.06
    [Any
    0.06
     Neutral
    0.06
    üt
    0.06
     dumb
    0.06
     notch
    0.06
    alue
    0.06
    回归
    0.06
     BOOLEAN
    0.06
    Act Density 0.022%

    No Known Activations