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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote varying degrees of adequacy, similarity, and difference among subjects

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

    comparing or qualifying qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bibfield
    -0.47
    Peny
    -0.42
    MessageTagHelper
    -0.42
    appré
    -0.42
     Tatsache
    -0.41
     fatica
    -0.40
    tecido
    -0.40
    edizione
    -0.38
    お客
    -0.38
    ųjų
    -0.38
    POSITIVE LOGITS
     ujednoznacz
    0.81
     تضيفلها
    0.61
     Italijani
    0.60
    HasAnnotation
    0.59
     Normdatei
    0.58
    Controllo
    0.55
    astéroïdes
    0.53
     noqa
    0.51
    VYMaps
    0.50
    CppMethod
    0.50
    Act Density 0.079%

    No Known Activations