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

    Neuronpedia

    INDEX
    Explanations

    statements about necessities and recommendations in various contexts

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

    preceding desirability or necessity

    np_acts-logits-general · gemini-2.0-flash

    advisable recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رشف
    -0.80
     Efq
    -0.79
    "]]
    -0.78
     nakalista
    -0.78
    PRNewswire
    -0.72
    "])
    -0.71
    ')")
    -0.71
    PreferredItem
    -0.68
     ویکی‌پدی
    -0.68
    ')))
    -0.67
    POSITIVE LOGITS
     advisable
    0.86
     advised
    0.79
     recommended
    0.73
     recommend
    0.72
     empfiehlt
    0.69
     conseille
    0.63
     recommends
    0.63
     wise
    0.63
    advised
    0.62
     рекомендуется
    0.62
    Act Density 0.166%

    No Known Activations