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

    Neuronpedia

    INDEX
    Explanations

    treatment when no cure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мүмк
    0.51
     thêm
    0.50
    思考
    0.50
     показывать
    0.49
     ተጨማሪ
    0.49
    每天
    0.48
     анализ
    0.48
    органи
    0.46
     શિક્ષણ
    0.46
     valutazione
    0.46
    POSITIVE LOGITS
    avi
    0.46
    ،
    0.41
     Branches
    0.41
    cure
    0.41
    igation
    0.40
    ggac
    0.40
     duniya
    0.39
    iri
    0.38
     rabbis
    0.38
    options
    0.38
    Act Density 0.016%

    No Known Activations