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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and API calls

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

    Values from URLs or code, often after an equals sign

    np_acts-logits-general · gemini-2.0-flash

    URL query parameter separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.62
    migrationBuilder
    -0.58
     riuscito
    -0.58
     שוליים
    -0.57
     invokingState
    -0.56
    /");
    -0.53
    /")
    -0.52
    IVEREF
    -0.51
    Externé
    -0.51
     Réponses
    -0.50
    POSITIVE LOGITS
    &
    1.70
    \&
    1.27
    }&
    1.25
     '&
    1.18
    +"&
    1.17
     "&
    1.14
    '&
    1.07
    .&
    1.06
    )&
    1.05
    &&
    1.05
    Act Density 0.289%

    No Known Activations