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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     اللّه
    0.42
     اللہ
    0.39
     Allah
    0.39
     αυτή
    0.38
    ⴻ
    0.38
    nah
    0.38
    Allah
    0.38
     nóng
    0.38
     metre
    0.37
    illah
    0.37
    POSITIVE LOGITS
    fier
    0.46
     T
    0.44
    चित
    0.40
     fier
    0.39
    вт
    0.39
    teries
    0.38
     द्वारा
    0.38
    טח
    0.37
     UK
    0.37
     Historically
    0.37
    Act Density 0.000%

    No Known Activations