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

    Neuronpedia

    INDEX
    Explanations

    phrases that identify or categorize concepts and ideas

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

    what is called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.75
     jspb
    -0.59
     ویکی‌پدی
    -0.57
     Biôgrafia
    -0.50
    ⓧ
    -0.49
    UserScript
    -0.49
    WithIOException
    -0.48
    __':
    -0.47
     antworte
    -0.46
    AnchorTagHelper
    -0.46
    POSITIVE LOGITS
     المعيارى
    0.52
    setObjectName
    0.40
    setViewportView
    0.39
    offsetof
    0.36
     referrerpolicy
    0.36
    optString
    0.35
     normal
    0.32
    getItemId
    0.32
    isDebugEnabled
    0.31
    rmtree
    0.31
    Act Density 0.265%

    No Known Activations