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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or concession

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

    in spite of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DotNetBar
    -0.57
    Kedua
    -0.52
     mukana
    -0.52
    Mereka
    -0.52
    ptăm
    -0.51
    macOS
    -0.50
    diğinde
    -0.50
     Przed
    -0.49
    Från
    -0.48
    Ahol
    -0.48
    POSITIVE LOGITS
     spite
    1.72
    printStackTrace
    0.55
     '{@
    0.52
    pite
    0.51
     Einfluß
    0.50
     pesar
    0.49
     apesar
    0.49
    setVerticalGroup
    0.48
     الرغم
    0.46
     مشين
    0.46
    Act Density 0.003%

    No Known Activations