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

    Neuronpedia

    INDEX
    Explanations

    lesson plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theseKeys
    0.44
     издания
    0.39
     gut
    0.39
     uncoated
    0.39
     unatt
    0.38
     extruded
    0.38
     getchar
    0.38
    व्यों
    0.38
     pressed
    0.38
    遒
    0.37
    POSITIVE LOGITS
    Lesson
    0.64
     lesson
    0.63
    lesson
    0.61
     Lesson
    0.61
     урок
    0.59
    planned
    0.57
     planned
    0.57
    教學
    0.56
    Teaching
    0.55
    teaching
    0.55
    Act Density 0.052%

    No Known Activations