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

    Neuronpedia

    INDEX
    Explanations

    bringing things or places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     la
    0.67
    La
    0.65
    )」
    0.59
     gana
    0.55
    )
    0.55
    URA
    0.54
    </
    0.50
     La
    0.50
    গায়
    0.50
     conocer
    0.50
    POSITIVE LOGITS
     bring
    0.66
     पाण्याची
    0.62
     brengen
    0.61
     домой
    0.60
     brings
    0.59
     unes
    0.58
     trouxe
    0.57
     fromi
    0.57
    bring
    0.56
    现场
    0.56
    Act Density 0.036%

    No Known Activations