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

    Neuronpedia

    INDEX
    Explanations

    riddles and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assessments
    1.11
     KPIs
    1.07
     indices
    0.93
     reporting
    0.92
     values
    0.91
     consistently
    0.90
     metrics
    0.89
     data
    0.89
     indicators
    0.89
     issues
    0.88
    POSITIVE LOGITS
    巧妙
    1.16
     divertida
    1.12
     divertido
    1.10
     मजेदार
    1.03
    创建一个
    0.97
    Imagine
    0.93
     간단
    0.89
    を用意
    0.88
    Terror
    0.87
    Halloween
    0.86
    Act Density 0.019%

    No Known Activations