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

    Neuronpedia

    INDEX
    Explanations

    quotations and dialogue punctuation in the text

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

    setting "text" property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.57
    EndContext
    -0.44
     ninguém
    -0.41
     Anfitrión
    -0.40
    triple
    -0.39
     pouvoit
    -0.39
     apaixon
    -0.39
    correre
    -0.38
    เย
    -0.38
     celebrado
    -0.38
    POSITIVE LOGITS
    ngdoc
    0.55
    ViewBag
    0.54
     cherchés
    0.52
     Autorizaciones
    0.51
     Infórmanos
    0.51
    IBarButtonItem
    0.51
    chtenstein
    0.50
    ANDUM
    0.50
     Reichstag
    0.50
     ujednoznacz
    0.49
    Act Density 0.010%

    No Known Activations