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

    Neuronpedia

    INDEX
    Explanations

    changing paradigms and perceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     correctamente
    0.46
     correctly
    0.41
    优点
    0.40
     properly
    0.40
     правильно
    0.39
     correctement
    0.38
     высокой
    0.37
     poseb
    0.36
     buenas
    0.36
     improvements
    0.36
    POSITIVE LOGITS
     perceptions
    0.86
     priorities
    0.84
     paradigms
    0.79
     perception
    0.79
     attitudes
    0.77
     behavior
    0.73
     paradigm
    0.71
     paradigma
    0.71
     approaches
    0.70
     восприя
    0.70
    Act Density 0.065%

    No Known Activations