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

    Neuronpedia

    INDEX
    Explanations

    famous historical figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [],
    0.88
     ​​
    0.87
     koje
    0.85
     kaya
    0.83
     toko
    0.81
    Noun
    0.80
    nytimes
    0.80
    at
    0.79
    디
    0.79
     celeb
    0.79
    POSITIVE LOGITS
    丷
    0.92
    ஞ்ஞான
    0.91
    jší
    0.87
     Bài
    0.86
    esque
    0.86
    unov
    0.86
    ův
    0.85
    ли
    0.84
    кові
    0.82
    ن
    0.81
    Act Density 0.190%

    No Known Activations