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

    Neuronpedia

    INDEX
    Explanations

    alleged brutality and ancient combat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     влияние
    0.91
     acessar
    0.87
     влияния
    0.86
    Influence
    0.86
     probl
    0.83
     SMTP
    0.83
     trends
    0.83
     влия
    0.81
    trends
    0.81
     ego
    0.80
    POSITIVE LOGITS
     torture
    1.82
     genocide
    1.45
     atrocities
    1.42
     starvation
    1.36
     tortured
    1.32
     horrific
    1.32
     brutal
    1.31
     cruelty
    1.31
     massacre
    1.28
     coerced
    1.26
    Act Density 0.301%

    No Known Activations