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

    Neuronpedia

    INDEX
    Explanations

    baked goods and sandwiches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ف
    0.89
    <0x80>
    0.77
    ม
    0.72
    ções
    0.70
    ج
    0.68
    가가
    0.67
    ס
    0.65
     ک
    0.63
    the
    0.63
    ش
    0.61
    POSITIVE LOGITS
     茶
    0.63
     马
    0.61
    🍪
    0.59
     Cookie
    0.59
     关于
    0.58
    -
    0.58
    饼
    0.58
    堣
    0.58
    一段时间
    0.57
     Мак
    0.57
    Act Density 0.299%

    No Known Activations