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

    Neuronpedia

    INDEX
    Explanations

    requests for donations and assistance

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

    Requests or questions including "please", "tell", or "can you"

    np_acts-logits-general · gemini-2.0-flash

    please and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niosek
    -0.60
    vington
    -0.56
    FlatAppearance
    -0.55
    GEBURTS
    -0.54
    难怪
    -0.54
     choix
    -0.52
     néz
    -0.51
     getSource
    -0.51
     Мексичка
    -0.51
    こいつ
    -0.50
    POSITIVE LOGITS
     please
    2.88
    please
    2.52
     Please
    2.50
    Please
    2.42
     PLEASE
    2.31
    PLEASE
    2.07
     pls
    2.05
     plz
    2.00
     bitte
    1.74
     Pls
    1.67
    Act Density 0.262%

    No Known Activations