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

    Neuronpedia

    INDEX
    Explanations

    proper names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உலகின்
    1.08
     콘텐츠
    1.05
     vielfält
    0.98
    renerg
    0.97
     다양
    0.95
    commonly
    0.93
     നെറ്റ്‌വർ
    0.93
    ometimes
    0.92
    享有
    0.92
    🌍
    0.91
    POSITIVE LOGITS
     Mrs
    1.30
     Lady
    1.27
     Councillor
    1.25
     Deputy
    1.24
     Aunt
    1.23
     Jimmy
    1.23
     Sarah
    1.22
     Kate
    1.20
     Liam
    1.20
     Chloe
    1.19
    Act Density 0.199%

    No Known Activations