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

    Neuronpedia

    INDEX
    Explanations

    starts with introduction or overview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retorted
    0.39
    anolol
    0.38
    ंकित
    0.38
    bé
    0.38
     pozdě
    0.37
    ympathetic
    0.37
    𝗁
    0.37
    ైనా
    0.37
    trimenti
    0.37
    ត្ថ
    0.37
    POSITIVE LOGITS
     Introduction
    2.66
     introduction
    2.59
    Introduction
    2.59
    introduction
    2.41
     INTRODUCTION
    2.38
    INTRODUCTION
    2.31
     overview
    2.25
     introducción
    2.22
    Overview
    2.19
     Overview
    2.19
    Act Density 0.183%

    No Known Activations