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

    Neuronpedia

    INDEX
    Explanations

    `env` variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    brechen
    0.88
     enthalten
    0.87
     Leibn
    0.86
    مة
    0.84
    ยนต์
    0.84
    kyverno
    0.81
    ยนตร์
    0.80
     Salas
    0.79
            
    0.79
    höhe
    0.79
    POSITIVE LOGITS
    其
    0.90
    ్రీ
    0.88
    і
    0.81
     HO
    0.80
     conclusions
    0.78
     Фі
    0.78
     Ι
    0.78
     classification
    0.77
    美国
    0.77
    Фи
    0.75
    Act Density 0.002%

    No Known Activations