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

    Neuronpedia

    INDEX
    Explanations

    world bank, cup, or war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    全国
    0.86
    全國
    0.85
    iffen
    0.85
     draper
    0.77
     ji
    0.74
     plaid
    0.71
    过去的
    0.67
     dead
    0.67
    oka
    0.66
    घ्र
    0.66
    POSITIVE LOGITS
    WIDE
    1.12
    views
    1.04
     entier
    0.95
    widet
    0.91
     اجمع
    0.88
     entero
    0.87
    वाइड
    0.86
    Wide
    0.83
    AlignedText
    0.82
     Wide
    0.82
    Act Density 0.261%

    No Known Activations