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

    Neuronpedia

    INDEX
    Explanations

    descriptive words and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.54
     🤗
    0.54
     सिस्टम
    0.50
     След
    0.49
    ă
    0.47
     점점
    0.47
     கிட்டத்தட்ட
    0.47
    ऑक्साइड
    0.46
     Waiver
    0.46
     파일을
    0.46
    POSITIVE LOGITS
    ل
    0.72
    8
    0.62
    ات
    0.62
    G
    0.57
    ین
    0.56
    ث
    0.54
    ام
    0.54
    ли
    0.54
    म
    0.52
    l
    0.52
    Act Density 0.300%

    No Known Activations