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

    Neuronpedia

    INDEX
    Explanations

    death and sacrifice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trong
    -0.09
     Preference
    -0.09
     ใน
    -0.09
    ảm
    -0.08
    _PLUGIN
    -0.08
     Frank
    -0.08
     программ
    -0.08
    .dynamic
    -0.08
     조건
    -0.08
     Conditions
    -0.08
    POSITIVE LOGITS
     sacrifice
    0.09
     overcame
    0.09
     humiliation
    0.09
     ಗಾಯ
    0.09
     illnesses
    0.09
     illness
    0.08
     injury
    0.08
     смерть
    0.08
     injuries
    0.08
     doctrine
    0.08
    Act Density 0.019%

    No Known Activations