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

    Neuronpedia

    INDEX
    Explanations

    latex article class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terc
    0.50
     terbaru
    0.48
     vendas
    0.44
     ナ
    0.43
    Gö
    0.43
     pertama
    0.42
     deals
    0.42
     locomotive
    0.41
     carbono
    0.40
     vib
    0.40
    POSITIVE LOGITS
    溽
    0.46
     пон
    0.38
    喜欢的
    0.38
    мага
    0.37
    papier
    0.37
     Bruce
    0.37
    社会的
    0.37
    enc
    0.36
     রামগতি
    0.36
     через
    0.36
    Act Density 0.002%

    No Known Activations