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

    Neuronpedia

    INDEX
    Explanations

    learning models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     особенностей
    0.41
    ování
    0.36
    iany
    0.36
     belonged
    0.35
    untza
    0.35
    活躍
    0.34
    arete
    0.34
    acción
    0.34
    ওয়ায়
    0.33
    ellä
    0.33
    POSITIVE LOGITS
     personer
    0.56
    者に
    0.52
     authorities
    0.50
     വിഭാഗ
    0.50
     officers
    0.50
     व्यक्ती
    0.49
     personnes
    0.49
     newsletter
    0.48
    人士
    0.48
     researchers
    0.47
    Act Density 0.020%

    No Known Activations