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

    Neuronpedia

    INDEX
    Explanations

    customer agent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     growth
    1.03
    ट्
    1.03
     weights
    1.03
    growth
    1.01
     semilla
    1.01
    Growth
    1.00
     weight
    0.97
     crystals
    0.96
     enlargement
    0.95
     hydrazine
    0.95
    POSITIVE LOGITS
     servizio
    1.64
     atendimento
    1.62
     SERVICE
    1.61
     serviços
    1.60
     servicio
    1.60
     обслуживание
    1.58
     service
    1.58
    SERVICE
    1.57
     pelayanan
    1.56
     서비스
    1.55
    Act Density 0.761%

    No Known Activations