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

    Neuronpedia

    INDEX
    Explanations

    you believe or know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     오히려
    0.91
    க்கொள்
    0.80
     overall
    0.76
     explic
    0.75
    反而
    0.74
     அறிக
    0.72
     generality
    0.72
    实际上
    0.70
     specifically
    0.70
    觀察
    0.70
    POSITIVE LOGITS
     dream
    0.86
     alguna
    0.85
     dreaming
    0.84
    Dream
    0.79
     dreamy
    0.78
     dreamt
    0.78
     꿈
    0.77
     alguno
    0.77
     мечта
    0.76
     želite
    0.74
    Act Density 0.181%

    No Known Activations