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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     roku
    -0.27
    LOPT
    -0.26
    centage
    -0.25
     Engl
    -0.25
    å°ģ
    -0.25
    fuse
    -0.24
    ç¡®å®ļ
    -0.24
    座
    -0.24
    tor
    -0.24
     kop
    -0.24
    POSITIVE LOGITS
    çīĮåŃIJ
    0.27
     buckle
    0.26
     buck
    0.25
     necessarily
    0.25
    /from
    0.25
    以ä¸ĬçļĦ
    0.25
    çłĶ究åijĺ
    0.24
     above
    0.24
     assumed
    0.24
     inst
    0.24
    Act Density 0.008%

    No Known Activations

    This feature has no known activations.