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

    Neuronpedia

    INDEX
    Explanations

    section beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.52
    यला
    0.46
     mempunyai
    0.45
    =
    0.44
    remmo
    0.44
     etiam
    0.44
    也
    0.44
     други
    0.44
     also
    0.43
    𝟮
    0.43
    POSITIVE LOGITS
     Overview
    0.60
    mdash
    0.60
    amp
    0.56
     Übersicht
    0.56
     Introduction
    0.54
    า
    0.52
     Überblick
    0.50
     Theory
    0.49
     ก
    0.48
     L
    0.48
    Act Density 0.023%

    No Known Activations