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

    Neuronpedia

    INDEX
    Explanations

    **o**ver processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Additionally
    0.77
     στο
    0.77
    งาม
    0.76
    EE
    0.75
    warming
    0.75
    ध्यक्ष
    0.74
     العالمين
    0.73
    வைக்
    0.73
    মাধ্যমে
    0.72
    ံ့
    0.70
    POSITIVE LOGITS
    وعة
    0.70
    一本
    0.68
    ફ
    0.68
    యితే
    0.67
     aveva
    0.66
    posto
    0.66
    кат
    0.66
    股价
    0.66
     роботи
    0.66
    一個
    0.64
    Act Density 0.002%

    No Known Activations