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

    Neuronpedia

    INDEX
    Explanations

    introductory notes and considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logits
    0.46
     expts
    0.42
     macroph
    0.41
     elution
    0.38
     gluon
    0.38
     synapses
    0.38
     qubit
    0.38
     neutrinos
    0.38
     necrotic
    0.37
     muons
    0.37
    POSITIVE LOGITS
    Introduction
    0.46
    Disclaimer
    0.45
     Introduction
    0.45
    بسم
    0.43
    INTRODUCTION
    0.43
    Goal
    0.41
    Note
    0.41
     Overview
    0.41
    This
    0.40
     Goal
    0.39
    Act Density 0.579%

    No Known Activations