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

    Neuronpedia

    INDEX
    Explanations

    across the street

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.63
     انتخابات
    0.57
     cerim
    0.56
     grafts
    0.55
    ي
    0.55
    ul
    0.54
     región
    0.54
    ای
    0.54
     inici
    0.54
    besch
    0.54
    POSITIVE LOGITS
     напротив
    0.65
     Opposite
    0.62
    μα
    0.61
    n
    0.59
    ний
    0.58
    Lon
    0.58
    ковка
    0.57
     Gann
    0.56
    лый
    0.55
     opposite
    0.55
    Act Density 0.002%

    No Known Activations