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

    Neuronpedia

    INDEX
    Explanations

    disease, illness, punishment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mercial
    0.48
     contratación
    0.47
     नरेन्द्र
    0.45
     এসেছে
    0.44
     protective
    0.43
     President
    0.42
    ického
    0.41
     przyję
    0.41
    íst
    0.41
     käyttää
    0.40
    POSITIVE LOGITS
    疾病
    0.47
     hastalık
    0.46
     stupidity
    0.45
     misdemean
    0.43
     Krankheit
    0.43
     illnesses
    0.43
    โรค
    0.42
     maladies
    0.42
     Symptoms
    0.42
     singularities
    0.42
    Act Density 0.001%

    No Known Activations