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

    Neuronpedia

    INDEX
    Explanations

    references to collective experiences and opinions in societal contexts

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

    everyeveryoneeverythingeverywhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     durchaus
    -0.47
     espagne
    -0.46
    GenerationType
    -0.46
     całkow
    -0.45
     כן
    -0.44
     ponownie
    -0.44
     complètes
    -0.43
     tiegħek
    -0.43
     iconFacebook
    -0.42
     prestazioni
    -0.41
    POSITIVE LOGITS
     everybody
    0.56
     everywhere
    0.51
     Everybody
    0.47
    everybody
    0.46
     Everywhere
    0.44
    Everybody
    0.44
     everyone
    0.43
    Everywhere
    0.43
     EVERYONE
    0.43
     everything
    0.42
    Act Density 0.064%

    No Known Activations