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

    Neuronpedia

    INDEX
    Explanations

    class related terms and code operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    خصة
    0.79
     {
    0.71
     ஒன்றை
    0.69
     almost
    0.64
     समित
    0.64
     (%
    0.64
     (@
    0.63
    ?=
    0.62
     ®
    0.62
     vom
    0.61
    POSITIVE LOGITS
    class
    1.35
     class
    1.29
     kelas
    1.01
    クラス
    0.99
     클래
    0.97
     Class
    0.96
     clase
    0.95
     classe
    0.94
     класу
    0.93
     کلاس
    0.91
    Act Density 0.061%

    No Known Activations