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

    Neuronpedia

    INDEX
    Explanations

    listing or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кус
    0.52
     حالات
    0.48
    Mounted
    0.44
    История
    0.44
     kus
    0.44
     வரலா
    0.43
    ة
    0.43
    以上の
    0.43
     또는
    0.42
     PHOT
    0.41
    POSITIVE LOGITS
    डमी
    0.49
    spl
    0.43
    roger
    0.43
     ओर
    0.43
    enity
    0.40
     بدی
    0.40
     screwing
    0.40
     prioritized
    0.39
     simpler
    0.39
     درسنا
    0.39
    Act Density 0.002%

    No Known Activations