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

    Neuronpedia

    INDEX
    Explanations

    essay and composition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FAQs
    0.52
    👇
    0.51
     list
    0.51
     👇
    0.51
     UK
    0.50
     detailed
    0.50
     OK
    0.50
     sectors
    0.49
     approx
    0.48
     yachts
    0.47
    POSITIVE LOGITS
    Essay
    0.59
    essay
    0.55
     Essay
    0.49
    Ethan
    0.46
     essay
    0.46
    作文
    0.44
    高中
    0.42
    进而
    0.42
    학년
    0.40
    简洁
    0.40
    Act Density 0.031%

    No Known Activations