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

    Neuronpedia

    INDEX
    Explanations

    networking and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    媜
    0.41
    सबुक
    0.40
     schade
    0.38
     semblables
    0.38
     attho
    0.38
    ﻁ
    0.38
    न्देल
    0.38
     пунктов
    0.38
     cơ
    0.37
     caractéristique
    0.37
    POSITIVE LOGITS
    ria
    0.39
    hide
    0.38
    eg
    0.37
     Є
    0.36
    ec
    0.36
     FC
    0.36
     नांद
    0.36
     صل
    0.35
     result
    0.35
    øm
    0.35
    Act Density 0.003%

    No Known Activations