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

    Neuronpedia

    INDEX
    Explanations

    look for answers/clues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sentenced
    0.74
    𝔀
    0.74
     मृतकों
    0.70
     knocked
    0.70
     několik
    0.69
    𝓢
    0.69
    ческой
    0.68
    fica
    0.68
    BinaryOperation
    0.67
    δου
    0.67
    POSITIVE LOGITS
    로
    0.88
     kiếm
    0.87
    に
    0.64
    та
    0.60
    뵙
    0.60
     hiểu
    0.58
    엔
    0.58
     tratti
    0.58
    ми
    0.57
     apa
    0.57
    Act Density 0.218%

    No Known Activations