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

    Neuronpedia

    INDEX
    Explanations

    killing, murder, death, assassination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     smoky
    0.45
     늘
    0.37
     projetos
    0.37
     progetti
    0.36
     тем
    0.35
     progetto
    0.35
     enabled
    0.34
     영향을
    0.34
     सेकेंडरी
    0.34
     flattering
    0.34
    POSITIVE LOGITS
     fatally
    0.55
    trag
    0.51
     murió
    0.51
     tragic
    0.48
     killed
    0.47
     قتل
    0.47
     tragically
    0.46
     trag
    0.46
     murdered
    0.45
     murder
    0.44
    Act Density 0.032%

    No Known Activations