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

    Neuronpedia

    INDEX
    Explanations

    the presence of the start-of-document token

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

    mathematical notation or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numberWith
    -0.73
    𝟶
    -0.59
     dentaire
    -0.56
    DotNetBar
    -0.54
     démocr
    -0.54
    Cordialement
    -0.54
     waited
    -0.53
    WithFormat
    -0.52
     Abonnez
    -0.51
    glClear
    -0.50
    POSITIVE LOGITS
    ItemBackground
    0.65
    GraphicsUnit
    0.63
     allAfrica
    0.58
    NavController
    0.53
    AddTagHelper
    0.52
    お話
    0.52
    rungsseite
    0.51
    ConstraintMaker
    0.50
     InputDecoration
    0.50
    IVEREF
    0.50
    Act Density 0.216%

    No Known Activations