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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .Categories
    -0.07
    �
    -0.07
    énergie
    -0.07
    小吃
    -0.07
     территор
    -0.07
     jogador
    -0.06
    .geometry
    -0.06
    �
    -0.06
    _container
    -0.06
    ,");↵
    -0.06
    POSITIVE LOGITS
    aille
    0.07
    alen
    0.07
    declare
    0.07
    _nullable
    0.07
     Paw
    0.07
    ضح
    0.07
     kas
    0.06
    柔和
    0.06
     Maher
    0.06
    !("{}",
    0.06
    Act Density 0.002%

    No Known Activations