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

    Neuronpedia

    INDEX
    Explanations

    ¡Hola Spanish greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veículos
    0.50
    ｢
    0.46
    кугӀ
    0.43
     migraines
    0.43
     thrombo
    0.43
     primarySwatch
    0.43
    getahuan
    0.42
     članak
    0.42
    廁
    0.42
     interstitiis
    0.42
    POSITIVE LOGITS
     {
    0.40
    ↵
    0.40
    hi
    0.39
    absolutely
    0.38
    yiz
    0.38
     jin
    0.37
    once
    0.37
     prin
    0.36
    hello
    0.36
    ag
    0.36
    Act Density 0.008%

    No Known Activations