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

    Neuronpedia

    INDEX
    Explanations

    then: you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    अप
    0.40
    рту
    0.40
    োগ্য
    0.39
    ільки
    0.38
    每年
    0.38
    тировать
    0.38
    ственную
    0.37
     бази
    0.37
    كما
    0.37
     års
    0.37
    POSITIVE LOGITS
    dg
    0.43
    ख
    0.42
    linewidth
    0.40
    ll
    0.38
     ဖ
    0.38
     yields
    0.37
     gol
    0.37
     yield
    0.37
    adj
    0.36
     toolbar
    0.36
    Act Density 0.004%

    No Known Activations