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

    Neuronpedia

    INDEX
    Explanations

    INVEST principle and connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ứng
    0.41
    展開
    0.41
     पर्दे
    0.41
    لات
    0.39
    ‌اند
    0.38
    していますが
    0.37
    гү
    0.37
     لذلك
    0.37
     नुक
    0.37
     करण्यास
    0.36
    POSITIVE LOGITS
    riteria
    0.46
     Probab
    0.43
     propagator
    0.43
     โม
    0.43
     bhave
    0.42
     Calyce
    0.42
    彝
    0.42
     vinto
    0.41
     ร
    0.41
     squadra
    0.41
    Act Density 0.005%

    No Known Activations