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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    нда
    1.07
     soyez
    1.07
     ইতিহাসে
    1.06
    ฯ
    1.06
    ер
    1.05
     sinais
    1.02
    stacks
    1.00
     sabes
    0.99
     serupa
    0.98
     сын
    0.98
    POSITIVE LOGITS
    го
    1.04
    га
    1.04
    ваты
    1.04
    ∈
    1.00
    тила
    0.99
    চূ
    0.98
    arns
    0.98
    ூட்
    0.98
    জ
    0.95
    最具
    0.94
    Act Density 1.322%

    No Known Activations