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

    Neuronpedia

    INDEX
    Explanations

    urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.39
    0.33
    /.
    0.33
    s
    0.29
     that
    0.28
    +
    0.28
    /)
    0.28
     &
    0.27
    </em>
    0.27
    /,
    0.27
    POSITIVE LOGITS
    鳇
    0.35
     تساوي
    0.35
    蟶
    0.33
    عيه
    0.33
     acide
    0.33
    <unused262>
    0.33
     শুকনো
    0.32
    <unused439>
    0.31
    বনে
    0.31
     außergewöhn
    0.31
    Act Density 0.040%

    No Known Activations