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

    Neuronpedia

    INDEX
    Explanations

    mention of specific organizations, places, or groups

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

    Tokens after publication titles or dates

    np_acts-logits-general · gemini-2.0-flash

    news articles with dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.71
     Commencez
    -0.67
     autorytatywna
    -0.58
    〒
    -0.56
     aidé
    -0.55
    Привет
    -0.54
    الإنجليزية
    -0.53
    kezés
    -0.53
     فريبيس
    -0.52
    Уважаемые
    -0.52
    POSITIVE LOGITS
     news
    1.08
    news
    0.90
     article
    0.88
     News
    0.86
     headlines
    0.84
    News
    0.84
     Reporters
    0.82
    article
    0.81
     journalists
    0.76
     notícia
    0.76
    Act Density 0.151%

    No Known Activations