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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating interest or awareness of various topics and issues

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

    knowing and wondering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.56
    #+#
    -0.48
    évaluateur
    -0.48
    RenderAtEndOf
    -0.47
     InputDecoration
    -0.47
     ब्रेकडाउन
    -0.47
     يتيمه
    -0.46
    yyj
    -0.45
     المعيارى
    -0.45
     ویکی‌آمباردا
    -0.44
    POSITIVE LOGITS
    日閲覧
    0.43
     propOrder
    0.38
     mergeFrom
    0.38
    XmlEnum
    0.37
     their
    0.36
    elemField
    0.35
     themselves
    0.34
     ModelRenderer
    0.34
    labelledby
    0.33
     vym
    0.33
    Act Density 0.073%

    No Known Activations