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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ﻧ
    1.08
     커
    1.06
    стром
    0.99
     부
    0.99
     το
    0.99
     εξε
    0.98
     studi
    0.98
     multe
    0.98
    pä
    0.97
     불
    0.97
    POSITIVE LOGITS
    ب
    1.29
    ták
    1.26
     exuber
    1.18
    ה
    1.17
     parques
    1.13
    ignores
    1.12
    imon
    1.12
    y
    1.11
    ्स
    1.11
     sanctity
    1.09
    Act Density 0.000%

    No Known Activations