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

    Neuronpedia

    INDEX
    Explanations

    data loading and population

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    д
    0.59
     odio
    0.58
    дт
    0.57
     perspici
    0.56
    د
    0.55
     saddhim
    0.55
     trenut
    0.54
    णसी
    0.53
    менова
    0.53
     liga
    0.52
    POSITIVE LOGITS
    י
    0.74
     aw
    0.65
    o
    0.63
    i
    0.62
     e
    0.61
    1
    0.60
     p
    0.60
     cuticle
    0.59
    ി
    0.59
    Inn
    0.58
    Act Density 0.002%

    No Known Activations