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

    Neuronpedia

    INDEX
    Explanations

    list of negative attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dedicato
    0.49
    ᓐ
    0.46
     ornate
    0.46
     désigne
    0.44
     striées
    0.43
     идеально
    0.41
     boul
    0.40
     impressively
    0.40
     doskona
    0.40
     parfaitement
    0.40
    POSITIVE LOGITS
     immoral
    0.67
     injustice
    0.63
     mismanagement
    0.58
     irresponsible
    0.57
     व्यवहार
    0.55
     कायद्या
    0.55
     hardships
    0.55
     unethical
    0.55
     selfishness
    0.55
     injustices
    0.55
    Act Density 0.001%

    No Known Activations