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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     patented
    1.10
    杖
    1.05
    ς
    0.97
    दीश
    0.95
    ভিতে
    0.94
    ים
    0.94
    एस
    0.93
     havia
    0.92
    ਆਂ
    0.92
     soften
    0.92
    POSITIVE LOGITS
    o
    1.13
    الم
    0.91
    ه
    0.86
    कारों
    0.85
    𝐤
    0.85
    вання
    0.85
    currentIndex
    0.85
    jší
    0.84
    ილ
    0.84
     colnames
    0.84
    Act Density 0.001%

    No Known Activations