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

    Neuronpedia

    INDEX
    Explanations

    perceived moral situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     direc
    0.44
     warmup
    0.42
     directorio
    0.41
     contribut
    0.40
    lite
    0.39
    权重
    0.39
    OfWeek
    0.39
     interests
    0.38
     discounts
    0.38
    服装
    0.38
    POSITIVE LOGITS
     masterpiece
    0.46
     manusia
    0.45
     tragedy
    0.43
    這位
    0.40
     Elon
    0.39
    这位
    0.39
     Wahrheit
    0.39
    那位
    0.38
    ╯
    0.38
     انکار
    0.38
    Act Density 0.000%

    No Known Activations