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

    Neuronpedia

    INDEX
    Explanations

    concepts related to safety and protection

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

    safety and danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.51
     հղումներ
    -0.51
     Normdatei
    -0.50
    bibfield
    -0.50
     initComponents
    -0.48
    AddHtmlAttribute
    -0.47
    Sno
    -0.46
    MLLoader
    -0.46
     gärna
    -0.45
    siasi
    -0.45
    POSITIVE LOGITS
     safety
    0.72
    Safety
    0.69
    safety
    0.68
     SAFETY
    0.62
     Safety
    0.62
     sécurité
    0.59
     bezpieczeństwa
    0.57
     Sicherheit
    0.57
     Sécurité
    0.56
     seguridad
    0.56
    Act Density 0.023%

    No Known Activations