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

    Neuronpedia

    INDEX
    Explanations

    locations and origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Бүгенге
    0.45
    鉞
    0.42
     вя
    0.40
    燄
    0.37
    ពេលវេល
    0.36
     HBO
    0.36
    엇
    0.36
     ποι
    0.36
    数据的
    0.36
    ត់
    0.35
    POSITIVE LOGITS
     Illinois
    0.53
     California
    0.52
     native
    0.52
     Wir
    0.52
     Hertfordshire
    0.51
     suburban
    0.49
    埼玉
    0.49
     Danville
    0.49
     Sudbury
    0.49
     Florida
    0.48
    Act Density 0.002%

    No Known Activations