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

    Neuronpedia

    INDEX
    Explanations

    specific nouns after "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сервер
    0.42
     formatting
    0.38
     vicinity
    0.38
     جایی
    0.36
     definizione
    0.35
     confines
    0.35
     instance
    0.34
     instances
    0.34
     ranks
    0.33
     copies
    0.33
    POSITIVE LOGITS
     ابن
    0.35
    amas
    0.35
    Aire
    0.34
    âr
    0.34
    etic
    0.33
    4
    0.33
    ological
    0.33
     الذين
    0.33
    ﻟ
    0.33
     trois
    0.32
    Act Density 0.100%

    No Known Activations