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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    strom
    0.70
    лле
    0.67
     आपने
    0.66
    cherry
    0.66
    achel
    0.66
     Controvers
    0.66
    APs
    0.65
     ने
    0.65
    yer
    0.64
    مر
    0.63
    POSITIVE LOGITS
    s
    0.89
     sexes
    0.82
     compilers
    0.81
    τυ
    0.80
     дзяржа
    0.80
     ability
    0.78
     genders
    0.77
    ség
    0.77
    ларни
    0.77
     enjoyment
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.