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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated operations or formatting in programming contexts

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

    Code-related questions or instructions

    np_acts-logits-general · gemini-2.0-flash

    programming questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -1.70
    -0.73
    bootstrapcdn
    -0.70
    ")){
    -0.64
    ↵↵↵↵↵
    -0.64
    '){
    -0.63
    ↵↵↵
    -0.62
    ↵↵↵↵↵↵↵
    -0.60
    <eos>
    -0.59
    "){
    -0.59
    POSITIVE LOGITS
     surla
    0.72
     ویکی‌پدیای
    0.62
     CommonModule
    0.57
    PMailer
    0.55
    itinéraire
    0.54
     propOrder
    0.54
    Gemeinden
    0.53
     grà
    0.53
    tvguidetime
    0.52
     Paglinawan
    0.51
    Act Density 0.143%

    No Known Activations