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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     blazing
    1.46
    樘
    1.35
     весьма
    1.32
     leverage
    1.27
    писы
    1.22
     reigning
    1.22
    ীনে
    1.21
     γλώ
    1.21
     leaderboard
    1.20
     handlebars
    1.20
    POSITIVE LOGITS
    ní
    1.19
    nove
    1.16
    ं
    1.15
    nie
    1.10
    ен
    1.07
    ال
    1.05
     vitam
    1.03
    ELIG
    1.03
     बरो
    1.03
    الع
    1.01
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.