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

    Neuronpedia

    INDEX
    Explanations

    question starters and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ak
    1.29
    ة
    1.21
    ل
    1.16
    ين
    1.13
    أ
    1.13
    at
    1.11
    يا
    1.09
    к
    1.08
    ر
    1.06
    ي
    1.06
    POSITIVE LOGITS
     youre
    0.80
    clientsdetails
    0.79
     क्यो
    0.75
     theyre
    0.75
     furtherance
    0.74
    gruppe
    0.74
     GoObject
    0.73
    hase
    0.72
     theres
    0.71
     arent
    0.71
    Act Density 0.031%

    No Known Activations