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

    Neuronpedia

    INDEX
    Explanations

    describing states or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     echte
    1.32
    iness
    1.32
     disband
    1.31
     verschiedenen
    1.29
     gays
    1.29
    word
    1.24
     bosses
    1.22
     FTE
    1.20
    дру
    1.20
    国
    1.19
    POSITIVE LOGITS
    ‌ترین
    1.67
     ترین
    1.58
    ताएं
    1.50
    mente
    1.39
    izamos
    1.36
     للغاية
    1.35
    ভাবে
    1.35
    ly
    1.35
    iteit
    1.32
    ता
    1.31
    Act Density 1.256%

    No Known Activations