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

    Neuronpedia

    INDEX
    Explanations

    Vice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xiety
    0.59
    etzungen
    0.59
    것
    0.59
     myfile
    0.59
    ματος
    0.57
    ষুধ
    0.57
    ettiva
    0.55
    тся
    0.55
    ácil
    0.55
    iqueness
    0.55
    POSITIVE LOGITS
     directeur
    0.75
     director
    0.72
     Director
    0.70
     directo
    0.66
     Commander
    0.63
     impresion
    0.63
     prosecutor
    0.61
     Executive
    0.61
     billionaire
    0.61
    总裁
    0.61
    Act Density 0.002%

    No Known Activations