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

    Neuronpedia

    INDEX
    Explanations

    phrases and questions related to clarification or inquiry about specific subjects

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

    about which or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rueda
    -0.32
    Гео
    -0.32
     recognize
    -0.32
    ع
    -0.32
     encontraban
    -0.32
    leuchte
    -0.31
    ówek
    -0.31
     Innov
    -0.30
     Slo
    -0.30
     assist
    -0.30
    POSITIVE LOGITS
     about
    1.04
    about
    0.96
     ABOUT
    0.95
     About
    0.94
    About
    0.93
     tentang
    0.83
    關於
    0.82
    ABOUT
    0.80
     apie
    0.80
     Tentang
    0.79
    Act Density 0.085%

    No Known Activations