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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and elements of dialogue

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

    Code snippets and XML-related words

    np_acts-logits-general · gemini-2.0-flash

    we now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.66
     للاسماء
    -0.56
    optionalTypeArgs
    -0.56
     ब्रेकडाउन
    -0.55
     ویکی‌پدی
    -0.54
    RTEE
    -0.54
    لينكات
    -0.53
    jsxFileName
    -0.52
    XmlAccessorType
    -0.52
     estekak
    -0.52
    POSITIVE LOGITS
    hObject
    0.50
    Clik
    0.48
    Grid
    0.46
    Absor
    0.42
    XML
    0.42
    Parents
    0.42
     Turbul
    0.41
    HTML
    0.41
    Liverpool
    0.40
    Existing
    0.40
    Act Density 0.175%

    No Known Activations