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

    Neuronpedia

    INDEX
    Explanations

    comprehension and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    錡
    0.37
     ház
    0.35
    面に
    0.35
    ্যাট
    0.33
    enka
    0.33
     کہتے
    0.32
    YX
    0.32
    setBadgeText
    0.32
    ineuse
    0.32
    ቒ
    0.32
    POSITIVE LOGITS
     understanding
    3.83
     understand
    3.70
    理解
    3.63
    understanding
    3.59
     Understanding
    3.56
    Understanding
    3.52
    understand
    3.48
     understands
    3.47
     Understand
    3.41
    Understand
    3.39
    Act Density 0.489%

    No Known Activations