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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "first" in contexts related to notable achievements or historical milestones

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

    First time something happened

    np_acts-logits-general · gemini-2.0-flash

    first woman to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Various
    -0.66
     getItemId
    -0.64
    OrBuilder
    -0.64
    middels
    -0.63
    ArrowToggle
    -0.63
    resave
    -0.62
    various
    -0.62
     îna
    -0.60
     Various
    -0.60
     Administrativna
    -0.60
    POSITIVE LOGITS
     ever
    0.90
     fully
    0.82
     truly
    0.82
     jemals
    0.81
     directly
    0.80
     completely
    0.80
     publicly
    0.78
     explicitly
    0.75
     réellement
    0.75
     überhaupt
    0.74
    Act Density 0.394%

    No Known Activations