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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ik
    0.59
    𝗶
    0.56
    ர்
    0.54
     tujuh
    0.53
    ো
    0.52
    м
    0.52
    n
    0.50
     करीब
    0.50
     tils
    0.49
    m
    0.49
    POSITIVE LOGITS
     suffice
    0.74
    字段
    0.65
     doomed
    0.65
     Concise
    0.65
     devoid
    0.65
     formatted
    0.65
     keepsake
    0.64
     suffices
    0.63
     scratched
    0.62
     idéale
    0.62
    Act Density 4.889%

    No Known Activations