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

    Neuronpedia

    INDEX
    Explanations

    logic, assumptions, and plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unités
    0.52
    Ꮫ
    0.47
    ཌ
    0.46
    大量的
    0.45
    ທາງ
    0.45
     mangas
    0.45
    山市
    0.44
    ᖃ
    0.44
     systèmes
    0.44
    önig
    0.43
    POSITIVE LOGITS
     -
    0.55
    <li>
    0.54
    <ul>
    0.44
    vil
    0.43
     ^{-
    0.41
     restrain
    0.41
    />
    0.40
    </h3>
    0.40
    ,]$
    0.40
    ATION
    0.40
    Act Density 0.000%

    No Known Activations