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

    Neuronpedia

    INDEX
    Explanations

    section markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مؤرشف
    0.50
     niemand
    0.50
     ἀ
    0.47
     Δεν
    0.46
    ଲେ
    0.46
     імені
    0.44
    Ⓘ
    0.44
     ܒ
    0.43
    ქვ
    0.42
     États
    0.42
    POSITIVE LOGITS
    参数
    0.55
     advantages
    0.51
    )：
    0.50
     packing
    0.50
    ）：
    0.49
     Chengdu
    0.48
    ①
    0.48
     Guangzhou
    0.48
     Advantages
    0.46
     vantagens
    0.46
    Act Density 0.002%

    No Known Activations