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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mens
    -0.07
     connexion
    -0.06
     unset
    -0.06
    订
    -0.06
    係
    -0.06
     الك
    -0.06
    .launch
    -0.06
     Kub
    -0.06
     hod
    -0.06
    ris
    -0.06
    POSITIVE LOGITS
    thal
    0.08
    打印机
    0.07
    ,user
    0.07
    _ajax
    0.07
    舞台
    0.07
     такие
    0.07
    員工
    0.07
    Workers
    0.07
    サービ
    0.07
    (tag
    0.07
    Act Density 0.027%

    No Known Activations