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

    Neuronpedia

    INDEX
    Explanations

    determiner + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्युअर
    1.08
    ॅम्प
    0.90
     които
    0.87
     извър
    0.86
     въз
    0.86
     Якщо
    0.84
     всеки
    0.82
     пър
    0.82
     спеціа
    0.80
     Уен
    0.80
    POSITIVE LOGITS
     investigación
    0.98
     música
    0.98
     único
    0.98
     sistema
    0.98
     guerra
    0.98
     tipo
    0.98
     trabajo
    0.96
     tecnología
    0.96
     grupo
    0.95
     estado
    0.95
    Act Density 0.355%

    No Known Activations