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

    Neuronpedia

    INDEX
    Explanations

    romance, ballet, femme, force, excellence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manipulations
    0.43
     manip
    0.42
     rustic
    0.42
     Interesting
    0.42
     pistes
    0.41
     ціка
    0.40
    Rustic
    0.40
     interesting
    0.40
     interesantes
    0.40
     euros
    0.40
    POSITIVE LOGITS
     refinement
    0.48
     revisited
    0.45
     trom
    0.45
    trom
    0.45
    Exception
    0.44
     Empire
    0.41
     exception
    0.41
     universe
    0.40
     Exception
    0.40
     refined
    0.39
    Act Density 0.006%

    No Known Activations