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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power dynamics and governance issues

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

    invading territory or places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.52
    tvguidetime
    -0.49
    ScopeManager
    -0.47
    fjspx
    -0.47
    AddHtmlAttribute
    -0.45
    ⤹
    -0.45
    bewerken
    -0.41
    httphttps
    -0.39
    recette
    -0.39
    MemoryWarning
    -0.38
    POSITIVE LOGITS
    Климат
    0.50
     оригіналу
    0.50
    EDEFAULT
    0.45
    uxxxx
    0.43
    Wald
    0.43
     appelez
    0.41
     للاسماء
    0.40
    MIDDLEWARE
    0.39
    دانشنامهٔ
    0.38
    Билгалдахарш
    0.37
    Act Density 0.107%

    No Known Activations