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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ירוש
    -0.07
     псих
    -0.06
    _titles
    -0.06
    лина
    -0.06
     прим
    -0.06
    _tl
    -0.06
     Bek
    -0.06
     Pleasant
    -0.06
     trag
    -0.06
     Islamist
    -0.06
    POSITIVE LOGITS
     kicking
    0.08
    ductor
    0.07
     preprocess
    0.07
    劑
    0.07
     música
    0.07
    清洗
    0.07
     оборудование
    0.07
    UNDLE
    0.07
    工厂
    0.07
     Lola
    0.07
    Act Density 0.077%

    No Known Activations