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

    Neuronpedia

    INDEX
    Explanations

    python files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آیت
    0.90
     immagini
    0.87
     JSX
    0.87
     afbeelding
    0.86
     indignation
    0.85
    পূর্বে
    0.83
     feminism
    0.81
     تصاویر
    0.81
    絃
    0.80
     삶
    0.80
    POSITIVE LOGITS
    லா
    0.63
    ogany
    0.60
     distant
    0.58
     puc
    0.57
     know
    0.57
    }{}
    0.56
    ropathy
    0.56
     paid
    0.55
     தூ
    0.55
     furthest
    0.54
    Act Density 0.016%

    No Known Activations