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

    Neuronpedia

    INDEX
    Explanations

    concepts related to evidence, methodologies, and conditions related to scientific validation and experimentation

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

    demonstrates, settings, option, role, determining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.59
    fromnode
    -0.56
     arşivlendi
    -0.52
     noDo
    -0.45
    tagPool
    -0.45
    <h1>
    -0.44
    点此举报
    -0.43
    fjspx
    -0.43
     Numerade
    -0.42
    tagext
    -0.42
    POSITIVE LOGITS
     المعيارى
    0.56
     '\\;'
    0.52
    RegressionTest
    0.50
     Wikimedijinoj
    0.49
    AnchorStyles
    0.47
     AssemblyCulture
    0.47
    FXML
    0.45
    Przypisy
    0.44
    IsContent
    0.43
    urlpatterns
    0.41
    Act Density 0.255%

    No Known Activations