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

    Neuronpedia

    INDEX
    Explanations

    goal and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pourtant
    0.45
     Pourtant
    0.42
     fortunately
    0.42
     môžete
    0.41
     récentes
    0.41
     შეგი
    0.40
     nevertheless
    0.39
     यूं
    0.39
     unglaublich
    0.39
     enthusiasts
    0.39
    POSITIVE LOGITS
    Emphasis
    0.93
     Emphasis
    0.91
    Goal
    0.84
     цель
    0.84
     goal
    0.80
     هدف
    0.80
     emphasis
    0.80
     Goal
    0.78
     목표
    0.78
     الهدف
    0.78
    Act Density 0.046%

    No Known Activations