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

    Neuronpedia

    INDEX
    Explanations

    punctuation followed by articles or markdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nghĩ
    0.46
     उल्लंघन
    0.44
     Drugs
    0.43
     lack
    0.43
     избежать
    0.43
    觉得
    0.42
    asambhavam
    0.41
    قی
    0.40
    统计
    0.40
     અન્ય
    0.40
    POSITIVE LOGITS
     olefin
    0.51
    。
    0.43
    それぞれの
    0.41
    =
    0.41
     jednot
    0.40
    olefin
    0.40
     geometrical
    0.39
    strdup
    0.39
    btn
    0.38
    <0x89>
    0.38
    Act Density 0.039%

    No Known Activations