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

    Neuronpedia

    INDEX
    Explanations

    templating languages and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    2.05
    o
    1.75
    ে
    1.48
    y
    1.47
    ع
    1.46
    th
    1.37
    িয়ে
    1.37
    но
    1.35
    os
    1.35
    кси
    1.32
    POSITIVE LOGITS
     sidew
    1.43
    ರಳ
    1.38
     adjuster
    1.36
     шрифт
    1.35
     tooltip
    1.35
    ರವ
    1.32
     இதனால்
    1.32
     captions
    1.31
     പങ്കെടു
    1.31
     readability
    1.30
    Act Density 0.028%

    No Known Activations