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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     necessário
    0.41
    葵
    0.41
     Когда
    0.38
     vol
    0.38
     Gen
    0.37
     Ná
    0.37
     hend
    0.37
     Най
    0.37
    ParallelGroup
    0.37
     necesaria
    0.37
    POSITIVE LOGITS
     enthusiasm
    0.45
     উৎসাহ
    0.42
     entusiasmo
    0.42
    jpe
    0.41
    振
    0.40
     emocion
    0.40
    oscill
    0.40
    collect
    0.38
    整理
    0.38
     plaintext
    0.38
    Act Density 0.001%

    No Known Activations