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

    Neuronpedia

    INDEX
    Explanations

    sexualization and objectification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Votre
    0.58
    Nicht
    0.56
    Puede
    0.55
    Mediterr
    0.54
    María
    0.53
    Pokud
    0.52
    你说
    0.52
    วัสดี
    0.51
    Você
    0.51
    Chicken
    0.50
    POSITIVE LOGITS
     MAPK
    0.51
     election
    0.49
     тя
    0.47
     markdown
    0.47
     twinning
    0.47
     GDPR
    0.47
     elections
    0.46
     nominated
    0.46
     Markdown
    0.46
     democratization
    0.46
    Act Density 0.003%

    No Known Activations