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

    Neuronpedia

    INDEX
    Explanations

    sissy wife, freshman, chin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    творе
    0.43
    क्षेप
    0.40
    OCC
    0.40
    narr
    0.40
    未来
    0.39
    ﻧ
    0.39
    нци
    0.39
     define
    0.38
     kitt
    0.38
    umma
    0.37
    POSITIVE LOGITS
     इकट्ठा
    0.46
    ุ
    0.44
     empat
    0.44
     uncontrollable
    0.44
     Αυ
    0.43
    ্টা
    0.43
    țit
    0.43
     adultes
    0.43
     facial
    0.42
     supérieur
    0.42
    Act Density 0.002%

    No Known Activations