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

    Neuronpedia

    INDEX
    Explanations

    programming language import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     și
    0.49
     và
    0.43
     dgn
    0.43
    ActionPerformed
    0.42
    และ
    0.41
     и
    0.41
     අපි
    0.40
     Nationalist
    0.40
    ajući
    0.40
     Popup
    0.39
    POSITIVE LOGITS
     wert
    0.41
     évent
    0.39
     тре
    0.38
    وم
    0.38
    يف
    0.38
    เวอร์
    0.37
    ളാ
    0.36
    é
    0.36
     custo
    0.36
    基本上
    0.36
    Act Density 0.004%

    No Known Activations