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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     odnos
    0.41
     RACE
    0.38
    馀
    0.38
    绻
    0.37
     век
    0.37
    myItemType
    0.36
    按
    0.36
     инду
    0.35
     прогноз
    0.35
     सूफ़ी
    0.35
    POSITIVE LOGITS
    ])):
    0.44
     ដ
    0.40
     interviewer
    0.38
     kelahiran
    0.37
     oyunc
    0.36
    狷
    0.36
    ктери
    0.36
     ليصل
    0.36
    บบ
    0.35
    velopper
    0.35
    Act Density 0.000%

    No Known Activations