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

    Neuronpedia

    INDEX
    Explanations

    D

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appellants
    1.20
    ра
    1.14
    inė
    0.99
    ค
    0.99
     donations
    0.99
    ラ
    0.98
     protesters
    0.97
    ഘടന
    0.97
    ર
    0.96
     initiatives
    0.95
    POSITIVE LOGITS
     ব্যায়াম
    0.86
     varit
    0.85
     расска
    0.78
     Dot
    0.77
     vikt
    0.77
    aside
    0.74
    Dot
    0.72
     nunca
    0.72
    сть
    0.71
    ように
    0.71
    Act Density 0.001%

    No Known Activations