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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    秏
    0.51
     Nbd
    0.48
     Bz
    0.47
     Humidity
    0.46
     srcs
    0.45
     или
    0.44
     Irak
    0.44
     Hoffnung
    0.43
    এত
    0.43
     rồi
    0.43
    POSITIVE LOGITS
     '
    0.39
    نا
    0.39
     job
    0.38
     πλα
    0.38
    idaire
    0.37
     **
    0.37
    loc
    0.36
    ito
    0.36
    سان
    0.36
    4
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.