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

    Neuronpedia

    INDEX
    Explanations

    protecting valuables and integrity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oue
    0.40
     nabíd
    0.39
    incomplete
    0.38
    悶
    0.38
     designer
    0.38
    pressing
    0.37
    滌
    0.37
    Expire
    0.36
    ভাসের
    0.36
    اولة
    0.35
    POSITIVE LOGITS
     integrity
    1.00
     integridad
    0.87
    integrity
    0.84
    を守
    0.83
     sanctity
    0.83
     precious
    0.80
     protect
    0.79
     protéger
    0.79
     vulnerable
    0.79
     schützen
    0.77
    Act Density 0.084%

    No Known Activations