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

    Neuronpedia

    INDEX
    Explanations

    formal to casual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    与
    0.45
     από
    0.43
    と
    0.43
    부터
    0.42
     અને
    0.41
     până
    0.41
     terhadap
    0.40
    性と
    0.40
    との
    0.40
    자와
    0.40
    POSITIVE LOGITS
     να
    0.50
     atthakath
    0.43
    ovala
    0.42
    ToArabic
    0.42
    ಮಾಡ
    0.41
    ಪಾ
    0.40
     ==>
    0.39
     frases
    0.39
     zu
    0.38
     کردیا
    0.38
    Act Density 0.020%

    No Known Activations