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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    章节
    0.41
     hacia
    0.41
     Specialist
    0.39
     オレンジ
    0.39
     ది
    0.38
     души
    0.38
     спе
    0.38
    向
    0.37
    rivit
    0.37
     تجاه
    0.37
    POSITIVE LOGITS
    ities
    0.43
    Parent
    0.41
     Parent
    0.38
    Grouping
    0.37
     child
    0.37
    Group
    0.36
    Traits
    0.36
     baby
    0.36
     wasn
    0.36
    Weak
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.