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

    Neuronpedia

    INDEX
    Explanations

    references to security systems and their effectiveness

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

    security and privacy threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sc
    -0.40
     story
    -0.35
     cra
    -0.35
    fon
    -0.33
    story
    -0.32
    sc
    -0.32
    บ
    -0.32
     Fon
    -0.31
    doc
    -0.31
     Bon
    -0.30
    POSITIVE LOGITS
     security
    0.71
     Sicherheit
    0.71
     SECURITY
    0.70
     Security
    0.70
     Sécurité
    0.69
     CreateTagHelper
    0.68
     cybersecurity
    0.67
     Segurança
    0.65
     Cybersecurity
    0.65
    Security
    0.65
    Act Density 0.039%

    No Known Activations