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

    Neuronpedia

    INDEX
    Explanations

    water parks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mischiev
    0.43
     fikir
    0.42
     безу
    0.42
     כבר
    0.41
     demurrer
    0.40
     dettag
    0.40
     узнать
    0.40
     بدأ
    0.40
     awe
    0.40
     تعریف
    0.40
    POSITIVE LOGITS
     Liquids
    0.50
    redients
    0.48
     Beverages
    0.47
    하다
    0.46
     evacuation
    0.46
     for
    0.46
    health
    0.45
     liquids
    0.45
    slash
    0.44
    next
    0.43
    Act Density 0.010%

    No Known Activations