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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     două
    0.41
    ม
    0.41
     térmica
    0.40
    ナ
    0.39
    ﻤ
    0.38
    山の
    0.38
     vē
    0.37
    .
    0.37
     violência
    0.37
     cinéma
    0.37
    POSITIVE LOGITS
    ak
    0.61
    il
    0.58
    ik
    0.55
    ers
    0.52
    i
    0.51
    ir
    0.51
    و
    0.50
     insecticides
    0.50
    ie
    0.49
    anel
    0.49
    Act Density 3.924%

    No Known Activations