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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    esub
    -0.30
     pinch
    -0.25
    æĹłçº¿
    -0.25
    ictionaries
    -0.25
    第ä¸Ģ
    -0.24
    onio
    -0.24
     rushes
    -0.24
    ç§ĺå¯Ĩ
    -0.24
    aleza
    -0.24
    roys
    -0.23
    POSITIVE LOGITS
    讲述
    0.27
     hel
    0.27
    ned
    0.26
    Hel
    0.26
    æľ¬æĽ¸
    0.26
     al
    0.24
    DEX
    0.24
    gram
    0.24
    ड
    0.24
    çļĦä¹łæĥ¯
    0.23
    Act Density 0.009%

    No Known Activations

    This feature has no known activations.