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

    Neuronpedia

    INDEX
    Explanations

    virtues

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     शक्तिशाली
    0.47
     intensively
    0.47
     unrel
    0.45
     potente
    0.44
     puissant
    0.42
     intensely
    0.42
    密集
    0.42
     poderoso
    0.41
     poderosa
    0.41
     가능한
    0.41
    POSITIVE LOGITS
     patience
    1.64
     discernment
    1.59
     awareness
    1.48
     humility
    1.48
     foresight
    1.48
     thoughtfulness
    1.47
     empathy
    1.44
     prudence
    1.38
     discretion
    1.37
    awareness
    1.34
    Act Density 0.508%

    No Known Activations