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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     costing
    0.45
     rufis
    0.39
     donnent
    0.38
     consuming
    0.37
     spends
    0.37
    дент
    0.36
     расход
    0.36
     femen
    0.35
     آتی
    0.35
     donn
    0.35
    POSITIVE LOGITS
    期待
    0.48
     subtle
    0.46
    Sav
    0.44
     सतर्क
    0.44
    灵活
    0.43
    faktor
    0.43
    itant
    0.42
    Hipp
    0.42
    രിച്ചത്
    0.41
     Sav
    0.40
    Act Density 0.002%

    No Known Activations