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

    Neuronpedia

    INDEX
    Explanations

    specific keywords in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    પણ
    0.48
    י
    0.47
     instal
    0.47
     riz
    0.45
    戙
    0.45
     flamb
    0.44
     Instal
    0.44
     radix
    0.44
     fester
    0.43
     Natale
    0.43
    POSITIVE LOGITS
    PLEX
    0.49
    در
    0.48
     فأ
    0.43
    hmen
    0.43
     مطرح
    0.42
    Arc
    0.41
     Pumps
    0.41
     لی
    0.41
    િક
    0.41
     گو
    0.41
    Act Density 0.001%

    No Known Activations