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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     instead
    -0.27
     grows
    -0.27
    ium
    -0.26
    instead
    -0.25
    :\"
    -0.25
    fähig
    -0.24
    ResponseStatus
    -0.23
    æĪIJéķ·
    -0.23
    cido
    -0.23
     Aur
    -0.23
    POSITIVE LOGITS
    æĺ¯æĪijçļĦ
    0.28
    routine
    0.27
    èĢ³æľµ
    0.26
    æĹ¥å¸¸
    0.26
    èĬĤæ°´
    0.26
    è°¯
    0.26
     routine
    0.25
     everyday
    0.25
    alog
    0.24
    è¿Ľåľº
    0.24
    Act Density 0.122%

    No Known Activations

    This feature has no known activations.