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

    Neuronpedia

    INDEX
    Explanations

    burada olmak çok güzel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Но
    0.98
    Под
    0.97
    Э
    0.95
    И
    0.94
     När
    0.94
    это
    0.93
     Га
    0.93
     Это
    0.93
     Но
    0.92
     Ин
    0.92
    POSITIVE LOGITS
     şekilde
    0.68
     birçok
    0.64
     olarak
    0.62
     olabilir
    0.61
     olacak
    0.60
     акчага
    0.60
     özellik
    0.60
     божомолдор
    0.59
     farklı
    0.59
     olan
    0.58
    Act Density 0.001%

    No Known Activations