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

    Neuronpedia

    INDEX
    Explanations

    restaurant starters and appetizers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이
    0.62
     pega
    0.60
    願い
    0.57
    に
    0.57
     mikä
    0.56
     imprime
    0.56
    سين
    0.55
    ดา
    0.55
     זה
    0.55
    の
    0.54
    POSITIVE LOGITS
     appetizers
    0.77
    companies
    0.62
    ﺑ
    0.61
    রাও
    0.58
     refreshments
    0.57
    ޏ
    0.57
     amusing
    0.57
    ť
    0.57
    aints
    0.55
     starters
    0.55
    Act Density 0.002%

    No Known Activations