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

    Neuronpedia

    INDEX
    Explanations

    code and programming-related terms and constructs

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

    Code, game, or programming related words

    np_acts-logits-general · gemini-2.0-flash

    game content: player cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "){
    -0.59
    ]='\
    -0.58
    '){
    -0.56
    `,
    -0.56
    '])){
    -0.56
     Folks
    -0.55
     workforce
    -0.55
    ckeye
    -0.54
    ')"
    -0.54
    ']='
    -0.54
    POSITIVE LOGITS
     ingame
    0.88
    gameserver
    0.78
     nerfed
    0.71
     randomized
    0.65
     gameplay
    0.64
     animations
    0.62
     playable
    0.61
     player
    0.61
     animation
    0.61
     game
    0.61
    Act Density 0.602%

    No Known Activations