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

    Neuronpedia

    INDEX
    Explanations

    various scripts and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spectacle
    0.50
    ﻱ
    0.46
    setBadge
    0.45
     މ
    0.45
    steak
    0.43
     Dünya
    0.43
     ጉዳ
    0.43
     lask
    0.43
    oyama
    0.42
    setFillColor
    0.42
    POSITIVE LOGITS
    >
    0.47
    ниях
    0.47
    س
    0.46
     марки
    0.45
    为
    0.44
    上的
    0.43
    ن
    0.43
    椅
    0.42
    از
    0.42
    沿
    0.42
    Act Density 0.000%

    No Known Activations