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

    Neuronpedia

    INDEX
    Explanations

    list in order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     của
    0.45
     জীবনী
    0.44
     рецен
    0.44
     даних
    0.44
    Ｘ
    0.43
    କୁ
    0.42
    Ｆ
    0.42
    🍤
    0.41
     структуры
    0.40
    ਾਈ
    0.40
    POSITIVE LOGITS
    くなる
    0.47
     animal
    0.47
     placebo
    0.45
     vasodil
    0.45
     homic
    0.45
     stork
    0.45
     welfare
    0.44
    لا
    0.43
     wal
    0.42
     caminar
    0.42
    Act Density 0.002%

    No Known Activations