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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     הבי
    0.48
    وفي
    0.44
    وبي
    0.40
     분명
    0.39
    वि
    0.38
     कैरी
    0.38
    фектив
    0.38
    ρί
    0.37
    Ví
    0.37
    俾
    0.37
    POSITIVE LOGITS
    tris
    0.41
    ks
    0.40
    KE
    0.39
     Ansel
    0.38
    INE
    0.38
    ভগ
    0.38
    KL
    0.37
    ist
    0.37
     zah
    0.36
    ke
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.