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

    Neuronpedia

    INDEX
    Explanations

    deaths and violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varied
    0.32
     deciduous
    0.29
     avantaj
    0.29
     Stateful
    0.29
     cardinality
    0.28
     stepper
    0.27
    都
    0.27
     primarily
    0.27
    ็ก
    0.27
     skillset
    0.27
    POSITIVE LOGITS
     assassination
    0.39
     терро
    0.33
     bombing
    0.33
     assassinated
    0.33
     murdered
    0.32
     قتل
    0.31
     bombed
    0.29
     commemorative
    0.29
     हत्याकांड
    0.29
    defeated
    0.29
    Act Density 0.066%

    No Known Activations