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

    Neuronpedia

    INDEX
    Explanations

    concatenated_list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不一樣
    1.02
    オル
    0.98
     다르
    0.98
    螞
    0.93
    相同
    0.89
     differ
    0.88
    不同
    0.87
    不一样
    0.87
     oder
    0.86
    พอ
    0.86
    POSITIVE LOGITS
    idity
    0.94
     Ian
    0.86
    rige
    0.85
     Ego
    0.85
     Stuart
    0.84
    ɨ
    0.80
     Wayne
    0.80
     Jamie
    0.80
    Jamie
    0.79
     Barrie
    0.79
    Act Density 0.613%

    No Known Activations