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

    Neuronpedia

    INDEX
    Explanations

    answers, explanations, or revealing clues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Queste
    0.52
     Knowing
    0.51
     myös
    0.49
     remplacer
    0.49
     zapewn
    0.49
     buat
    0.48
     vaiht
    0.47
     आंब
    0.47
    ambahkan
    0.47
     Recognize
    0.47
    POSITIVE LOGITS
    тил
    0.48
    ece
    0.46
    χυ
    0.46
    м
    0.45
    arella
    0.43
    Rocky
    0.43
    groups
    0.43
    кси
    0.43
    스와
    0.43
    Rok
    0.43
    Act Density 0.000%

    No Known Activations