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

    Neuronpedia

    INDEX
    Explanations

    lists and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ەوە
    0.38
     gastronom
    0.37
     Murt
    0.35
     diversa
    0.35
    ﮑ
    0.35
     gastronomic
    0.35
     adhé
    0.34
     espuma
    0.33
     сельскохозяй
    0.33
    ترح
    0.33
    POSITIVE LOGITS
     पद्धति
    0.41
    Quant
    0.38
     Quantification
    0.38
    取得了
    0.38
    উ
    0.37
    আই
    0.37
     intensity
    0.35
    最近
    0.35
    צים
    0.35
     dosages
    0.35
    Act Density 0.398%

    No Known Activations