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

    Neuronpedia

    INDEX
    Explanations

    bold for emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পট
    0.39
     თუ
    0.38
     Alignment
    0.37
     ছিন্ন
    0.37
    eneuve
    0.37
    ക്കളുടെ
    0.35
     Watering
    0.35
    鍒
    0.35
    ⢿
    0.35
    的声音
    0.35
    POSITIVE LOGITS
     bold
    0.85
     Bold
    0.77
    Bold
    0.73
    bold
    0.68
     boldness
    0.64
     bolder
    0.54
    BOLD
    0.53
     italic
    0.52
     italics
    0.51
     text
    0.50
    Act Density 0.008%

    No Known Activations