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

    Neuronpedia

    INDEX
    Explanations

    headers and formatting elements in textual documents

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

    markup followed by titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.46
    ronpa
    -0.40
    Rifer
    -0.36
    IVEREF
    -0.35
    WriteTagHelper
    -0.34
     Olímpicos
    -0.34
     Krone
    -0.34
     campagnes
    -0.33
    Véase
    -0.33
     Référence
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.58
    RTGC
    0.56
     oprot
    0.54
    الحياه
    0.52
    messageInfo
    0.51
    ksikon
    0.50
    setDo
    0.50
     createSlice
    0.48
     deported
    0.47
    RTHOOK
    0.45
    Act Density 0.048%

    No Known Activations