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

    Neuronpedia

    INDEX
    Explanations

    repeating decimals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hela
    0.59
     hele
    0.58
     strutt
    0.57
     seuls
    0.57
     selbst
    0.55
    ُوا
    0.55
     déjà
    0.54
     difficultés
    0.54
     سنگ
    0.54
     små
    0.54
    POSITIVE LOGITS
    𝑌
    0.62
    <0xA9>
    0.62
    んにちは
    0.62
    profiss
    0.62
    芝
    0.61
     asal
    0.60
     auxin
    0.60
    حق
    0.59
    nless
    0.59
    <0xBE>
    0.58
    Act Density 0.000%

    No Known Activations