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

    Neuronpedia

    INDEX
    Explanations

    comparison tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phenomena
    0.70
     though
    0.69
     pudi
    0.67
     legends
    0.67
     supplement
    0.66
     CONDITION
    0.66
     value
    0.66
     picture
    0.66
     exceed
    0.66
     flew
    0.65
    POSITIVE LOGITS
    classe
    0.91
     Și
    0.87
    ્યા
    0.86
    yanka
    0.86
    ит
    0.84
     இசை
    0.83
    łem
    0.83
    恜
    0.80
    фон
    0.80
    敂
    0.80
    Act Density 0.012%

    No Known Activations