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

    Neuronpedia

    INDEX
    Explanations

    categories and subtopics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SendData
    0.41
    보면
    0.40
    有时候
    0.39
     sometimes
    0.38
    orney
    0.38
    ாரி
    0.38
     trudno
    0.38
    asey
    0.37
     Sometimes
    0.37
    CLICK
    0.37
    POSITIVE LOGITS
    vocab
    0.44
    น์
    0.41
     сфер
    0.39
     כדי
    0.38
     hoped
    0.37
    ពួក
    0.37
     чтобы
    0.37
     பண்ட
    0.36
    Visible
    0.36
     প্রত্যা
    0.35
    Act Density 0.001%

    No Known Activations