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

    Neuronpedia

    INDEX
    Explanations

    text formatting and styling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     duž
    0.73
    Dio
    0.69
     सय
    0.68
    涳
    0.68
    힣
    0.66
     spacer
    0.63
     meme
    0.63
    গুন
    0.62
    pageToken
    0.62
     manj
    0.61
    POSITIVE LOGITS
     bold
    1.32
     Bold
    1.24
    bold
    1.23
    Bold
    1.18
     বোল
    1.10
    BOLD
    1.07
     Ital
    1.03
     boldness
    1.02
     italic
    0.98
     बोल्ड
    0.95
    Act Density 0.090%

    No Known Activations