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

    Neuronpedia

    INDEX
    Explanations

    religious entities and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    active
    0.68
    F
    0.66
     ۲
    0.63
    Ｉ
    0.63
    carbons
    0.62
    food
    0.61
    Ｂ
    0.60
    中
    0.60
    Music
    0.59
     २
    0.59
    POSITIVE LOGITS
    ع
    0.80
    ح
    0.68
    م
    0.66
    ق
    0.66
    ra
    0.64
    {
    0.64
    lla
    0.61
     on
    0.60
    li
    0.59
     Figura
    0.59
    Act Density 0.000%

    No Known Activations