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

    Neuronpedia

    INDEX
    Explanations

    the followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aucune
    0.64
     idő
    0.56
     aucun
    0.55
     були
    0.54
     alimentare
    0.54
     adhé
    0.54
     esclusivamente
    0.54
     bénéf
    0.53
     ليس
    0.53
     attuale
    0.53
    POSITIVE LOGITS
    (
    0.57
     (
    0.52
    ו
    0.43
     Machu
    0.42
    os
    0.41
     to
    0.40
     Galaxies
    0.40
     CPU
    0.39
    ो
    0.39
     NATO
    0.39
    Act Density 0.145%

    No Known Activations