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

    Neuronpedia

    INDEX
    Explanations

    references to gaming or role-playing terms

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

    the Hog's Head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vPvB
    -0.41
    
    -0.41
    PREFERRED
    -0.39
     تضيفلها
    -0.39
    getragen
    -0.38
    IRQn
    -0.38
    kuuta
    -0.37
     pleaſure
    -0.37
     ſch
    -0.36
     Majefty
    -0.35
    POSITIVE LOGITS
    $_['
    0.57
     Мексичка
    0.56
     Italijani
    0.54
     Meksiku
    0.52
     otomatig
    0.49
     Administrativna
    0.48
     okuyayım
    0.47
    postsleuth
    0.47
     ModelExpression
    0.46
     noDo
    0.46
    Act Density 0.037%

    No Known Activations