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

    Neuronpedia

    INDEX
    Explanations

    specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    हमने
    0.90
    ü
    0.90
     Bản
    0.88
     devastating
    0.86
    ћи
    0.84
    খ্যার
    0.80
     பெரும்
    0.80
     bezpečnost
    0.80
     आम्ही
    0.79
     neue
    0.78
    POSITIVE LOGITS
    または
    1.05
     dwellers
    1.03
     takers
    1.00
     Airy
    0.97
    或
    0.94
     sider
    0.93
     wizard
    0.92
     eaters
    0.91
    walkers
    0.91
    信息公示
    0.89
    Act Density 0.318%

    No Known Activations