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

    Neuronpedia

    INDEX
    Explanations

    mentions of research and publications related to scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    published, installed, verified, conducted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     too
    -0.38
    Pretty
    -0.34
     pretty
    -0.33
    Мор
    -0.31
     aurez
    -0.30
     trouxe
    -0.30
    Introduction
    -0.29
     što
    -0.29
    toBeTruthy
    -0.28
    featureID
    -0.28
    POSITIVE LOGITS
     pinulongan
    0.69
    Autoritní
    0.68
    Tikang
    0.65
    OGND
    0.65
    хьтан
    0.65
     AssemblyCulture
    0.64
     Chwiliwch
    0.64
     CreateTagHelper
    0.63
     يتيمه
    0.63
    MLLoader
    0.62
    Act Density 0.319%

    No Known Activations