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

    Neuronpedia

    INDEX
    Explanations

    lectures and course materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     researching
    0.42
    💋
    0.40
     trackers
    0.40
    कुर
    0.39
    ➩
    0.39
     racking
    0.39
    getpath
    0.39
    MenuActive
    0.38
     getpath
    0.38
    sciences
    0.38
    POSITIVE LOGITS
     Lecture
    1.03
     lecture
    1.02
    Lecture
    1.00
     Lectures
    0.89
     lectures
    0.87
    講
    0.85
    lecture
    0.80
     lectured
    0.80
    讲
    0.79
    Lect
    0.77
    Act Density 0.015%

    No Known Activations