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

    Neuronpedia

    INDEX
    Explanations

    that you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emphasizes
    0.20
     bırak
    0.18
     trenches
    0.18
     yaptı
    0.17
     defies
    0.17
     maximizes
    0.17
     revolver
    0.17
     ketiga
    0.17
    мага
    0.17
     aligns
    0.17
    POSITIVE LOGITS
    you
    0.24
     you
    0.23
    used
    0.23
    我們要
    0.21
    which
    0.21
     которую
    0.21
     जोकि
    0.21
    ซึ่ง
    0.20
     którą
    0.19
    même
    0.19
    Act Density 0.186%

    No Known Activations