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

    Neuronpedia

    INDEX
    Explanations

    fantasy names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     profitability
    0.35
     calificaciones
    0.30
     algoritmo
    0.29
     negócio
    0.28
     hábitos
    0.28
     productividad
    0.28
     lihtsalt
    0.28
     sostenibilidad
    0.28
     abogados
    0.28
     सब्सिडी
    0.27
    POSITIVE LOGITS
    Order
    0.30
    Female
    0.30
     humanoid
    0.30
    Faction
    0.30
    Azure
    0.29
    Discord
    0.29
    Guild
    0.29
     goblin
    0.28
     Goblin
    0.28
    Petra
    0.27
    Act Density 0.241%

    No Known Activations