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

    Neuronpedia

    INDEX
    Explanations

    web, pre, Porto, known, defining, local, cubed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.84
    2
    0.68
     is
    0.64
     komponen
    0.54
    ﺎ
    0.54
    ﺔ
    0.54
     的
    0.52
     alebo
    0.52
    。《
    0.52
    ۔
    0.50
    POSITIVE LOGITS
    스는
    0.58
     campsites
    0.57
    ens
    0.55
    이지만
    0.55
     insures
    0.55
    스
    0.55
     tattoos
    0.54
    hits
    0.54
     sweatshirts
    0.54
     addictions
    0.54
    Act Density 0.108%

    No Known Activations