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

    Neuronpedia

    INDEX
    Explanations

    dialogue quotations and interactions between characters

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

    Followed by a quote or question mark

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.88
    Lähteet
    -0.77
    ]")]
    -0.77
    queryInterface
    -0.77
     onOptions
    -0.72
    noinspection
    -0.70
     BrowserModule
    -0.70
    Дереккөздер
    -0.68
    migrationBuilder
    -0.67
    ButterKnife
    -0.67
    POSITIVE LOGITS
     you
    0.68
    You
    0.60
     your
    0.60
    you
    0.56
     You
    0.55
    Your
    0.53
    你现在
    0.51
     вас
    0.51
    jfree
    0.46
    your
    0.46
    Act Density 0.140%

    No Known Activations