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

    Neuronpedia

    INDEX
    Explanations

    branding, logos, design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    正確
    0.43
     सौरभ
    0.43
    슨
    0.39
     Improves
    0.39
    йки
    0.39
    不知道
    0.38
     estimés
    0.38
    推定
    0.38
    ገር
    0.38
    微妙
    0.38
    POSITIVE LOGITS
     radically
    0.45
     wrongdoing
    0.42
     amortization
    0.41
     hugely
    0.41
     massively
    0.40
    फारिश
    0.40
     provoc
    0.39
     competitor
    0.39
     lowercase
    0.39
    Тер
    0.39
    Act Density 0.002%

    No Known Activations