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

    Neuronpedia

    INDEX
    Explanations

    atrocities and conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     burgl
    0.40
     сели
    0.39
    ရင်း
    0.39
     thieves
    0.38
     জমির
    0.38
     সাহেব
    0.37
     stolen
    0.37
    স্টে
    0.37
     robbers
    0.37
    রিক
    0.36
    POSITIVE LOGITS
     કૃ
    0.48
     건
    0.44
    িপ্ত
    0.43
     घटनाएं
    0.42
     கலா
    0.42
     अत्याचार
    0.42
    nius
    0.41
     कृत
    0.40
     совер
    0.40
     अराज
    0.40
    Act Density 0.010%

    No Known Activations