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

    Neuronpedia

    INDEX
    Explanations

    special occasions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    statement
    0.37
     ประเทศ
    0.37
     माग
    0.36
    ск
    0.36
    info
    0.35
    INFRINGEMENT
    0.35
     त्यांना
    0.35
     страны
    0.34
     NSString
    0.34
    source
    0.34
    POSITIVE LOGITS
     pernikahan
    0.47
     wedding
    0.37
     butterflies
    0.36
     weddings
    0.35
    যুব
    0.35
     ungdom
    0.33
     turtles
    0.33
     rusty
    0.33
     college
    0.32
     Butterflies
    0.32
    Act Density 0.001%

    No Known Activations