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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     heen
    0.76
     hell
    0.75
     Chats
    0.74
     tho
    0.74
     Care
    0.71
     nee
    0.71
     Comrade
    0.71
    tho
    0.71
     одино
    0.71
     Diva
    0.71
    POSITIVE LOGITS
    ان
    1.05
    न
    0.80
    را
    0.80
    酋
    0.76
    انج
    0.74
    рите
    0.71
     पर्यटन
    0.71
    Decrement
    0.69
    ارية
    0.68
     diminu
    0.68
    Act Density 0.000%

    No Known Activations