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

    Neuronpedia

    INDEX
    Explanations

    significant sentences or phrases that express important assertions or ideas

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

    introduction of specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.51
    MemoryWarning
    -0.48
    AndEndTag
    -0.48
     Gegenteil
    -0.46
     invokingState
    -0.46
     Chwiliwch
    -0.45
    EndContext
    -0.45
    SuspendLayout
    -0.42
     Menschheit
    -0.41
     للمعارف
    -0.41
    POSITIVE LOGITS
    曖昧さ回避
    0.54
    ريكية
    0.46
     Drapeau
    0.45
     swimmer
    0.44
    Datuak
    0.44
     Sidd
    0.43
     Nord
    0.41
     trö
    0.41
     stripper
    0.41
     Trunc
    0.41
    Act Density 0.280%

    No Known Activations