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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     desarrollo
    -0.08
    演讲
    -0.08
    变迁
    -0.07
    divider
    -0.07
    プレゼント
    -0.07
    _greater
    -0.07
    _speed
    -0.07
    ことです
    -0.07
     instr
    -0.07
     domin
    -0.07
    POSITIVE LOGITS
     }]
    0.07
    .keras
    0.07
     zap
    0.07
    鞮
    0.06
     commenc
    0.06
    კ
    0.06
     }],↵
    0.06
    ܒ
    0.06
     retains
    0.06
    تقي
    0.06
    Act Density 0.003%

    No Known Activations