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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ص
    0.55
    तेल
    0.50
    凝聚
    0.47
    گے
    0.47
    清单
    0.47
    िना
    0.46
    满
    0.46
    ata
    0.46
     Pue
    0.46
    ↵
    0.46
    POSITIVE LOGITS
     vesting
    0.41
     modest
    0.41
     suelo
    0.40
     cree
    0.40
    нең
    0.40
     বর্ণের
    0.40
     dict
    0.40
    はもちろん
    0.40
     Verifica
    0.38
     site
    0.38
    Act Density 0.001%

    No Known Activations