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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Forschungs
    0.90
    ifying
    0.88
    机器人
    0.83
    증
    0.82
     שנה
    0.81
    ificazione
    0.81
     quei
    0.80
    h
    0.80
    backend
    0.80
     intérieure
    0.80
    POSITIVE LOGITS
    AGE
    0.85
    LLA
    0.85
     unscrupulous
    0.82
    STON
    0.80
    грама
    0.80
    еру
    0.80
    SLOW
    0.80
    ORE
    0.78
    ÓN
    0.78
    اہم
    0.78
    Act Density 0.002%

    No Known Activations