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

    Neuronpedia

    INDEX
    Explanations

    discussing, outlining, writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حتی
    0.49
     وحتى
    0.45
     এমনকি
    0.44
     costos
    0.44
    uenza
    0.43
    gat
    0.43
     случаях
    0.42
     einfach
    0.42
    的情况下
    0.42
     оплаты
    0.42
    POSITIVE LOGITS
    LEC
    0.46
    vær
    0.43
    DOT
    0.41
    PCB
    0.41
     DREAM
    0.41
    вис
    0.41
    驱动
    0.40
    Bsky
    0.40
    ່ວ
    0.39
    SON
    0.39
    Act Density 0.006%

    No Known Activations