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

    Neuronpedia

    INDEX
    Explanations

    food bank donations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ově
    0.46
    ய்ட
    0.40
    ົບ
    0.40
     Epilepsy
    0.39
    喈
    0.39
    可用
    0.39
    ເລັກ
    0.39
    骜
    0.39
    ılan
    0.38
     everytime
    0.38
    POSITIVE LOGITS
     pantry
    0.46
     incluyen
    0.46
     meals
    0.45
     food
    0.44
     comida
    0.44
     prepara
    0.44
    鹽
    0.43
     distribuzione
    0.43
     cocinar
    0.43
     armario
    0.43
    Act Density 0.006%

    No Known Activations