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

    Neuronpedia

    INDEX
    Explanations

    home advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ที่มี
    0.42
    自动
    0.40
     և
    0.40
    لكتر
    0.39
     automated
    0.39
     Automation
    0.38
     entryway
    0.38
    ที่จะ
    0.38
     technologies
    0.38
     citation
    0.38
    POSITIVE LOGITS
     гостей
    0.49
     viagens
    0.49
     (=
    0.47
     hjem
    0.47
     baš
    0.47
     conceded
    0.44
     ospiti
    0.44
     весьма
    0.43
     vorne
    0.42
    ið
    0.42
    Act Density 0.001%

    No Known Activations