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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    agal
    -0.09
    モデル
    -0.08
     blogger
    -0.07
     Vish
    -0.07
    宠
    -0.07
    辍
    -0.07
    (Employee
    -0.07
    рож
    -0.07
     Glacier
    -0.07
    养育
    -0.07
    POSITIVE LOGITS
     ks
    0.07
    .OK
    0.06
    每股
    0.06
     tys
    0.06
     chain
    0.06
     compan
    0.06
    멋
    0.06
    برشلون
    0.06
     disks
    0.06
    رب
    0.06
    Act Density 0.001%

    No Known Activations