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

    Neuronpedia

    INDEX
    Explanations

    academic excellence, securing URLs, feeling unwell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     educator
    0.66
     Educator
    0.55
    instructor
    0.54
    講師
    0.54
    teacher
    0.52
     टीचर
    0.50
     instructor
    0.50
     शिक्षक
    0.48
    教师
    0.48
    Teacher
    0.46
    POSITIVE LOGITS
     NOW
    0.52
     every
    0.50
     Now
    0.48
    NOW
    0.48
     now
    0.47
     those
    0.46
    Now
    0.45
     each
    0.45
     that
    0.45
     success
    0.43
    Act Density 0.000%

    No Known Activations