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

    Neuronpedia

    INDEX
    Explanations

    learning beginner instructor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    domain
    0.42
     interrogation
    0.41
    _
    0.40
    export
    0.39
     entendeu
    0.39
     metadata
    0.38
    思想
    0.38
     alertness
    0.38
     subpoena
    0.37
     subordinates
    0.37
    POSITIVE LOGITS
     Beginners
    0.89
     Beginner
    0.87
     beginners
    0.86
     beginner
    0.83
     instructors
    0.83
     instructor
    0.81
     Instructor
    0.80
     प्रशिक्
    0.68
    课程
    0.68
    Instructor
    0.67
    Act Density 0.205%

    No Known Activations