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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Carleton
    0.46
     Karel
    0.45
     Caesar
    0.45
     Carbohyd
    0.45
    詹
    0.44
     hệ
    0.44
     lengkap
    0.43
     César
    0.43
     сфере
    0.43
    状况
    0.43
    POSITIVE LOGITS
    /
    0.49
    ous
    0.46
    it
    0.45
    ita
    0.44
    et
    0.43
     vraiment
    0.43
     بواسطة
    0.43
    outine
    0.42
     originales
    0.42
    en
    0.42
    Act Density 0.006%

    No Known Activations