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

    Neuronpedia

    INDEX
    Explanations

    ed, edmund, eddie, edge, edible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    രെ
    0.47
    isely
    0.41
    ເຄ
    0.40
    း
    0.40
    ณฑ
    0.39
    jskich
    0.39
    erious
    0.39
    शील
    0.39
     erythemat
    0.39
     kennt
    0.38
    POSITIVE LOGITS
     ED
    0.94
     ed
    0.92
     Ed
    0.90
    Ed
    0.83
    ED
    0.65
     ईडी
    0.64
     éd
    0.64
     Edd
    0.63
     Eds
    0.61
     EDL
    0.61
    Act Density 0.016%

    No Known Activations