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

    Neuronpedia

    INDEX
    Explanations

    what you need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    悆
    0.50
    胞
    0.47
    昃
    0.45
    區
    0.44
    ห
    0.44
    存
    0.44
    ED
    0.44
    识别
    0.41
    नस
    0.41
    瓣
    0.41
    POSITIVE LOGITS
    </h3>
    0.46
     денег
    0.46
     penjualan
    0.46
     ventas
    0.44
     Produkt
    0.43
     bhij
    0.43
    em
    0.43
     produkt
    0.43
     vendas
    0.42
    вам
    0.42
    Act Density 0.001%

    No Known Activations