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

    Neuronpedia

    INDEX
    Explanations

    relative followed by comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Product
    0.68
    ayısıyla
    0.65
    Luke
    0.64
    Sea
    0.64
     फेंक
    0.63
    Equipment
    0.61
     সক
    0.59
    Sag
    0.58
    撻
    0.57
    Produ
    0.57
    POSITIVE LOGITS
     condominiums
    0.69
     prevalent
    0.67
     GIFs
    0.67
     Workmen
    0.66
     cartoons
    0.65
    सीजी
    0.65
     outlined
    0.65
     triggered
    0.65
    尔
    0.65
     animations
    0.65
    Act Density 0.001%

    No Known Activations