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

    Neuronpedia

    INDEX
    Explanations

    mentions of problems and issues related to technology or systems

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

    recently graduated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.45
     تضيفلها
    -0.45
     estekak
    -0.41
     Мексичка
    -0.37
     internetowa
    -0.36
    qrst
    -0.36
    Identyfik
    -0.35
    ințe
    -0.34
    ViewFeatures
    -0.34
    InsertCommand
    -0.34
    POSITIVE LOGITS
    +#+#
    0.47
     propOrder
    0.47
    httphttps
    0.46
    LabelTagHelper
    0.44
     المعيارى
    0.44
    ofire
    0.44
    featureID
    0.43
     ब्रेकडाउन
    0.42
    참고
    0.41
    träd
    0.41
    Act Density 0.036%

    No Known Activations