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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    بد
    1.08
    ه
    1.02
    ciences
    0.99
     iar
    0.96
    oost
    0.96
    溉
    0.95
    ку
    0.94
     ficción
    0.93
    मा
    0.90
    रूप
    0.88
    POSITIVE LOGITS
    \{\
    0.99
    trem
    0.94
     khỏi
    0.94
     поза
    0.92
    \{(
    0.91
    ખ્ય
    0.91
    াদ্র
    0.89
     হস্তে
    0.88
    siehe
    0.86
    ra
    0.86
    Act Density 0.058%

    No Known Activations