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

    Neuronpedia

    INDEX
    Explanations

    common myths, println macros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nove
    0.51
     타입
    0.47
     zuletzt
    0.45
     конститу
    0.45
     sitio
    0.44
     म्हणजेच
    0.43
     учиты
    0.43
     nyug
    0.42
    焔
    0.42
     ^{
    0.41
    POSITIVE LOGITS
    ↵↵
    0.51
    dding
    0.47
    ها
    0.47
    isión
    0.46
    Child
    0.44
    ঞ্জেল
    0.44
     Thornton
    0.44
     Boats
    0.43
    儿
    0.43
    子的
    0.42
    Act Density 0.003%

    No Known Activations