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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by quote or verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fleste
    1.71
    俩
    1.69
    enan
    1.58
     Portanto
    1.54
    ỏe
    1.48
    łego
    1.48
    garten
    1.48
    ットン
    1.45
     fuera
    1.42
    ร
    1.42
    POSITIVE LOGITS
    ди
    2.02
    ну
    1.88
     elucid
    1.84
    ли
    1.70
    ни
    1.69
    ا
    1.69
    ك
    1.67
    으로써
    1.65
    也
    1.62
     skyrock
    1.61
    Act Density 0.319%

    No Known Activations