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

    Neuronpedia

    INDEX
    Explanations

    staying up-to-date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gares
    0.84
    दो
    0.84
    wem
    0.82
    柰
    0.76
    ált
    0.76
    జేపీ
    0.75
    weiser
    0.74
    )}{
    0.73
    स्टल
    0.73
    łos
    0.72
    POSITIVE LOGITS
     modern
    0.80
     often
    0.79
     keep
    0.78
     updates
    0.77
     Contemporary
    0.74
     staying
    0.74
     keeps
    0.73
     update
    0.72
     keeping
    0.72
     আপডেট
    0.71
    Act Density 0.027%

    No Known Activations