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

    Neuronpedia

    INDEX
    Explanations

    obtain and interpret results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    indexing
    0.40
    ணைய
    0.39
    bares
    0.39
    barrels
    0.38
    icza
    0.38
    now
    0.38
    Leb
    0.37
    elum
    0.37
    ✪
    0.35
    ias
    0.35
    POSITIVE LOGITS
     interpret
    0.73
     interprets
    0.71
     récol
    0.62
     interpretación
    0.62
     obtain
    0.62
     obten
    0.61
     получать
    0.61
     interpreting
    0.61
    interpret
    0.60
     получить
    0.60
    Act Density 0.019%

    No Known Activations