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

    Neuronpedia

    INDEX
    Explanations

    processing during step protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     주로
    0.40
    elementReference
    0.40
    db
    0.39
     francese
    0.39
    iquant
    0.38
     adc
    0.38
     расходов
    0.38
    西哥
    0.37
    blocks
    0.37
     Sark
    0.37
    POSITIVE LOGITS
    herb
    0.38
    കരണ
    0.38
    〟
    0.38
    --------
    0.37
     flowering
    0.37
    olium
    0.37
    ជាង
    0.36
     tijdens
    0.36
    階段
    0.35
    橋
    0.35
    Act Density 0.000%

    No Known Activations