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

    Neuronpedia

    INDEX
    Explanations

    using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    0.62
    Ná
    0.56
     Ná
    0.52
     lesiones
    0.50
     größer
    0.50
     salario
    0.49
    ны
    0.48
     Zá
    0.47
     съем
    0.47
     Schä
    0.46
    POSITIVE LOGITS
     นี่
    0.42
     utilizes
    0.42
     Thursdays
    0.41
    breadcrumbs
    0.41
     uses
    0.40
     appetizers
    0.40
    0.40
     catalysts
    0.40
    utiliser
    0.40
    ↵↵
    0.40
    Act Density 0.001%

    No Known Activations