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

    Neuronpedia

    INDEX
    Explanations

    scams fraudulent urgent refund

    np_acts-logits-general · gemini-2.5-flash-lite

    cybersecurity scam and phishing content, especially email red flags, fraud/urgency alerts, and references to sensitive financial or account information.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     benthic
    0.43
    Setting
    0.43
     Bibliothek
    0.42
     Einstellung
    0.42
     Lesson
    0.41
     nomenclature
    0.40
     physiologically
    0.40
    之
    0.40
     revisions
    0.40
     Translations
    0.40
    POSITIVE LOGITS
    非法
    0.52
     urgente
    0.52
     urgently
    0.52
     refund
    0.51
     якобы
    0.51
     garantiert
    0.51
     guaranteed
    0.50
     scam
    0.50
    ㊙
    0.50
     refundable
    0.49
    Act Density 0.060%

    No Known Activations