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

    Neuronpedia

    INDEX
    Explanations

    unique identifiers or codes

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

    Follows a hyphen

    np_acts-logits-general · gemini-2.0-flash

    a variety of specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.72
     médicaux
    -0.62
    存于互联网档案馆
    -0.61
    اقرأ
    -0.61
    AndEndTag
    -0.61
     industriels
    -0.59
    ЧИТА
    -0.58
     dentaire
    -0.57
    Ayrıca
    -0.57
     imageNamed
    -0.56
    POSITIVE LOGITS
    Autoritní
    0.77
    RunAsync
    0.61
     👋
    0.60
     
    0.60
    adaptiveStyles
    0.54
    InvalidProtocol
    0.47
     The
    0.47
     In
    0.47
     createState
    0.46
    buzo
    0.45
    Act Density 0.247%

    No Known Activations