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

    Neuronpedia

    INDEX
    Explanations

    elements related to coding or programming syntax and structure

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

    CSS properties with pixel values

    np_acts-logits-general · gemini-2.0-flash

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enschappelijke
    -0.76
    ":[{
    -0.72
    ///</
    -0.71
    ']}
    -0.67
    Бахар
    -0.67
     Савезне
    -0.66
    ness
    -0.65
     "));
    -0.65
    (");
    -0.65
     */;
    -0.64
    POSITIVE LOGITS
     nostru
    0.67
     policiales
    0.62
    írus
    0.61
     affich
    0.60
    seamnă
    0.58
     inconnu
    0.58
     humains
    0.57
     hendes
    0.56
    ertos
    0.55
     restantes
    0.54
    Act Density 0.287%

    No Known Activations