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

    Neuronpedia

    INDEX
    Explanations

    ever followed by past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    외부
    0.65
     Dispose
    0.60
    鬣
    0.59
     endeav
    0.58
    в
    0.57
     wymag
    0.57
    जनिक
    0.57
     Usual
    0.57
     представитель
    0.56
     সানডে
    0.56
    POSITIVE LOGITS
     naïve
    0.66
    𝑖
    0.63
    िस
    0.62
    සි
    0.62
    tiin
    0.62
    য়া
    0.60
    ্ধ্য
    0.60
     léger
    0.60
     baya
    0.59
     વર્ષ
    0.59
    Act Density 0.005%

    No Known Activations