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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ñ
    1.21
    ായ
    1.07
    一个
    1.03
    ه
    1.00
    startGame
    0.97
     Forgot
    0.94
    ää
    0.94
     Worked
    0.94
     hike
    0.91
    과
    0.90
    POSITIVE LOGITS
     règle
    1.49
    mos
    1.45
    man
    1.43
     kebak
    1.40
    guo
    1.37
     partenariat
    1.36
    鶯
    1.32
    кому
    1.32
     związku
    1.32
     основным
    1.31
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.