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

    Neuronpedia

    INDEX
    Explanations

    words followed by "in"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ris
    0.35
     باب
    0.34
    ઉસ
    0.34
     nesta
    0.34
     آذ
    0.34
    IsIn
    0.34
    Dans
    0.34
     बरो
    0.33
     anis
    0.33
    ucius
    0.33
    POSITIVE LOGITS
     în
    0.70
     in
    0.65
     فى
    0.59
     në
    0.51
     فِي
    0.50
     σε
    0.46
     في
    0.46
     по
    0.45
    ใน
    0.44
    ្នុង
    0.42
    Act Density 0.049%

    No Known Activations