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

    Neuronpedia

    INDEX
    Explanations

    run directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     just
    1.05
     simply
    0.89
     only
    0.81
     फक्त
    0.79
     simplement
    0.73
     Just
    0.70
     лишь
    0.67
    just
    0.67
     if
    0.67
     merely
    0.66
    POSITIVE LOGITS
     demandas
    0.97
    <unused1674>
    0.96
     getMain
    0.94
     Colombeau
    0.91
    忿
    0.90
    辕
    0.89
    izadas
    0.89
    पूजा
    0.89
    <unused142>
    0.89
     sifatida
    0.88
    Act Density 0.012%

    No Known Activations