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

    Neuronpedia

    INDEX
    Explanations

    so-called, determines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ulteriori
    0.44
    反而
    0.36
     Theo
    0.36
     Archivlink
    0.36
    仍
    0.35
     오히려
    0.35
    히려
    0.34
     ακόμα
    0.34
     Oakland
    0.34
     Starbucks
    0.34
    POSITIVE LOGITS
     sogenannte
    0.61
     sogen
    0.54
     sogenannten
    0.52
     आपल्याला
    0.52
     কীভাবে
    0.49
     определяет
    0.47
     determinar
    0.45
    两大
    0.45
    duh
    0.44
     четы
    0.44
    Act Density 0.531%

    No Known Activations