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

    Neuronpedia

    INDEX
    Explanations

    a following noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     العديد
    0.44
     tzv
    0.44
    )_{\
    0.41
    的主要
    0.37
     chiefly
    0.36
     longitudinally
    0.36
    人們
    0.36
     종합
    0.36
     continuously
    0.36
    人们
    0.36
    POSITIVE LOGITS
     friend
    0.53
     phone
    0.51
     piece
    0.51
     miracle
    0.49
     cheeky
    0.49
     nice
    0.48
     nugget
    0.48
     girly
    0.48
     breather
    0.48
     joke
    0.48
    Act Density 0.698%

    No Known Activations