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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ց
    0.80
    )=(-
    0.78
     zmniejs
    0.77
     Использу
    0.76
     installing
    0.74
     ชื่อ
    0.74
     Erfahr
    0.72
    νης
    0.72
     Einstellungen
    0.71
     Nauchno
    0.71
    POSITIVE LOGITS
    耐心
    0.79
    啊
    0.74
    omized
    0.70
     ofrecemos
    0.70
    ⵣ
    0.70
     ακ
    0.70
    ojure
    0.68
    мости
    0.67
    安静
    0.67
    不
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.