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

    Neuronpedia

    INDEX
    Explanations

    model response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bouts
    0.88
     Myths
    0.85
    的能力
    0.84
     Rasp
    0.84
    绎
    0.84
     Treg
    0.83
    ସ
    0.83
    鋭
    0.81
     Limitations
    0.81
     fréqu
    0.80
    POSITIVE LOGITS
    ं
    0.95
    ל
    0.89
    ir
    0.85
    il
    0.84
    ानंद
    0.83
    ic
    0.83
     интернет
    0.81
    와
    0.80
    é
    0.80
    دهای
    0.77
    Act Density 0.000%

    No Known Activations