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

    Neuronpedia

    INDEX
    Explanations

    academic writing and coursework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     merch
    0.48
     affaires
    0.44
     oček
    0.44
    alım
    0.43
     yatırım
    0.42
    र्सन
    0.42
    າງ
    0.40
     miesią
    0.40
     okazji
    0.40
    ører
    0.40
    POSITIVE LOGITS
     Introduction
    0.62
     Essay
    0.61
     essay
    0.58
     Thesis
    0.55
     Dissertation
    0.54
     dissertation
    0.53
     CONTENTS
    0.53
     Describes
    0.53
     describes
    0.52
     INTRODUCTION
    0.52
    Act Density 0.000%

    No Known Activations