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

    Neuronpedia

    INDEX
    Explanations

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ور
    1.55
    и
    1.53
    ק
    1.50
    ا
    1.48
    ু
    1.48
    ра
    1.42
    го
    1.42
    唥
    1.40
    ت
    1.39
    <0xBC>
    1.31
    POSITIVE LOGITS
    상을
    1.44
    이라는
    1.38
    inthe
    1.32
    膑
    1.27
     intitulé
    1.26
     ailing
    1.20
    대를
    1.17
    상이
    1.17
     ills
    1.16
     organes
    1.15
    Act Density 0.014%

    No Known Activations