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

    Neuronpedia

    INDEX
    Explanations

    evokes feelings and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    روش
    0.44
    鳞
    0.43
     ಅಂಶ
    0.42
     приложений
    0.42
     করিবেন
    0.41
    校园
    0.41
     જવાબ
    0.41
    發現
    0.41
     クリーム
    0.41
    ريع
    0.40
    POSITIVE LOGITS
    сек
    0.40
     immortality
    0.37
     view
    0.37
    햐
    0.37
     geh
    0.37
    ijl
    0.36
     automated
    0.35
    opic
    0.35
     justified
    0.35
     corp
    0.35
    Act Density 0.001%

    No Known Activations