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

    Neuronpedia

    INDEX
    Explanations

    concise, specific, short answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yatırım
    0.49
     ব্যবসার
    0.48
     airports
    0.45
     বিনিয়োগ
    0.44
     bisnis
    0.42
     entrepreneurs
    0.41
    靝
    0.41
     enjoys
    0.41
    玩意
    0.40
     warranties
    0.40
    POSITIVE LOGITS
     paragraph
    0.54
     Paragraph
    0.51
     concise
    0.49
     paragraphs
    0.48
     paraphr
    0.48
     выска
    0.47
     reasoning
    0.46
     sentences
    0.46
     essay
    0.46
    response
    0.46
    Act Density 0.511%

    No Known Activations