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

    Neuronpedia

    INDEX
    Explanations

    trinomials and creatine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.63
     three
    0.60
     living
    0.60
     Museum
    0.59
    П
    0.57
     paper
    0.57
     holiday
    0.55
     badge
    0.55
     Holiday
    0.54
     biom
    0.54
    POSITIVE LOGITS
    اي
    0.68
    ubmit
    0.66
    اني
    0.64
     السوق
    0.63
     تلك
    0.63
    uyó
    0.63
     مشترك
    0.62
    {
    0.61
    اين
    0.61
    ётся
    0.61
    Act Density 0.002%

    No Known Activations