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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ق
    2.50
    ص
    2.08
    ش
    1.98
    h
    1.84
    い
    1.82
    ست
    1.75
    ం
    1.71
    venido
    1.70
    IA
    1.65
    Jug
    1.60
    POSITIVE LOGITS
    اً
    3.00
    ඤ
    1.98
    თვის
    1.95
    gruppe
    1.92
    tedir
    1.89
     pengukuran
    1.89
     egyes
    1.87
    ierung
    1.84
    ুমাত্র
    1.84
    bbene
    1.84
    Act Density 0.002%

    No Known Activations