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

    Neuronpedia

    INDEX
    Explanations

    multilingual content policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这也是
    0.48
     Popup
    0.42
     Rejo
    0.41
    ্দ
    0.40
     tämä
    0.40
    returns
    0.40
    return
    0.39
    ຕາມ
    0.39
    それが
    0.39
    ঙ্গের
    0.38
    POSITIVE LOGITS
    órm
    0.41
    зна
    0.40
     مصر
    0.40
     وط
    0.39
    ум
    0.36
     pyroph
    0.36
     ruth
    0.35
     velmi
    0.34
     مدت
    0.33
     मायने
    0.33
    Act Density 0.363%

    No Known Activations