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

    Neuronpedia

    INDEX
    Explanations

    structured outline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irittura
    0.48
     addirittura
    0.48
    들도
    0.42
    也會
    0.40
     아주
    0.40
    uradaki
    0.39
    少なくとも
    0.39
    也会
    0.38
    上也
    0.38
    也将
    0.37
    POSITIVE LOGITS
     intégré
    0.45
     itp
    0.41
     vibrant
    0.40
    嶄
    0.40
     Saltar
    0.39
     intégr
    0.37
     Перейти
    0.35
     integrado
    0.35
     integrates
    0.35
     coverage
    0.34
    Act Density 0.195%

    No Known Activations