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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ഒ
    0.47
    च्चय
    0.45
     വന്ന
    0.44
    Ü
    0.43
     रे
    0.43
     पे
    0.42
    Sleep
    0.42
     Cuts
    0.42
    lø
    0.41
    POSITORY
    0.41
    POSITIVE LOGITS
     motionless
    0.50
    ᱡ
    0.48
     enmity
    0.44
     venom
    0.44
    定量
    0.44
    いる
    0.43
    тво
    0.43
     dish
    0.42
    стати
    0.42
    我が
    0.42
    Act Density 0.001%

    No Known Activations