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

    Neuronpedia

    INDEX
    Explanations

    initialization or beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    1.03
     Cristó
    1.02
    3
    0.98
     Globalization
    0.93
     Finished
    0.91
    8
    0.89
     Global
    0.89
     Départ
    0.85
    6
    0.83
     ::
    0.82
    POSITIVE LOGITS
    鈣
    1.61
     matrimonial
    1.58
     orthodontic
    1.58
    管道
    1.54
    的操作
    1.52
    .‏
    1.48
    ших
    1.47
     وان
    1.47
     motives
    1.47
     المن
    1.45
    Act Density 0.094%

    No Known Activations