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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Outreach
    0.51
     outreach
    0.50
     grandmother
    0.50
    ן
    0.48
     kap
    0.47
    唇
    0.47
     Wu
    0.46
     Joey
    0.46
     Brooklyn
    0.46
     neighbourhoods
    0.46
    POSITIVE LOGITS
    рующий
    0.55
    PCS
    0.52
    ཐ
    0.50
     ಮತ್ತೆ
    0.50
     couche
    0.49
    ジング
    0.49
    ✔
    0.49
     TUN
    0.49
    看得
    0.48
    ㈡
    0.48
    Act Density 0.000%

    No Known Activations