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

    Neuronpedia

    INDEX
    Explanations

    largely accompanied by approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mol
    0.43
    вате
    0.42
    вайте
    0.41
    ก่
    0.40
    вени
    0.40
     Timeline
    0.40
    Small
    0.39
    ваясь
    0.39
    牖
    0.39
    ህል
    0.39
    POSITIVE LOGITS
    ដែលអាច
    0.40
     магистра
    0.40
     아
    0.39
     harem
    0.39
    シリ
    0.39
     jok
    0.39
    cedent
    0.38
    োলন
    0.38
     testacé
    0.38
     aérea
    0.38
    Act Density 0.003%

    No Known Activations