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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    钆
    -0.07
    plt
    -0.07
    הדפסה
    -0.07
    님
    -0.07
    Lisa
    -0.07
     lesb
    -0.07
    이나
    -0.07
    ᴢ
    -0.06
    奶油
    -0.06
    מות
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .attribute
    0.07
     fading
    0.07
     flood
    0.07
     Romans
    0.07
    行為
    0.07
     עומ
    0.06
     authorization
    0.06
     WATCH
    0.06
     APPRO
    0.06
    Act Density 0.315%

    No Known Activations