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

    Neuronpedia

    INDEX
    Explanations

    4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    घा
    0.42
     sulfates
    0.40
    graphs
    0.39
    令牌
    0.38
    家伙
    0.38
     graphs
    0.38
     graphql
    0.38
     ngươi
    0.38
     συ
    0.38
     х
    0.38
    POSITIVE LOGITS
     Assessing
    0.40
     Centre
    0.39
    잖아요
    0.38
    heimer
    0.37
     Working
    0.37
     Beloved
    0.36
     On
    0.35
     dreaming
    0.35
     recognising
    0.35
     unbek
    0.35
    Act Density 0.003%

    No Known Activations