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

    Neuronpedia

    INDEX
    Explanations

    countries and origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quả
    0.39
    晹
    0.39
     Want
    0.38
    ابية
    0.37
     Insect
    0.36
    트를
    0.36
    触
    0.36
     Arial
    0.36
    fty
    0.35
    larını
    0.35
    POSITIVE LOGITS
    producer
    0.54
    Serbia
    0.46
    आरआई
    0.46
     producer
    0.45
    François
    0.44
     நாடுகளில்
    0.44
    Austria
    0.43
    😑
    0.43
     anecdote
    0.42
    PIA
    0.42
    Act Density 0.008%

    No Known Activations