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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     affiche
    1.42
    یثیت
    1.35
    conductivity
    1.34
     Puedes
    1.32
     kunna
    1.29
    tedir
    1.24
    enes
    1.23
     Bridgewater
    1.21
    𝐯
    1.20
    Rand
    1.18
    POSITIVE LOGITS
    i
    1.39
    আ
    1.32
     ه
    1.12
     στον
    1.12
     هذه
    1.06
     със
    1.05
    ি
    1.02
    Фи
    1.02
     вот
    1.01
    â
    1.00
    Act Density 0.000%

    No Known Activations