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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong recommendations

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

    highly recommend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.43
     wetter
    -0.42
    INSEE
    -0.41
     Connectez
    -0.41
    請繼續往下閱讀
    -0.41
     виправивши
    -0.40
    InlineData
    -0.39
     enfans
    -0.38
    劃
    -0.38
    poem
    -0.37
    POSITIVE LOGITS
     Highly
    0.73
     recommend
    0.70
    recommend
    0.68
     highly
    0.68
    Highly
    0.66
    highly
    0.65
    Polecam
    0.62
     recommended
    0.61
    évaluateur
    0.59
     RECOMMEND
    0.59
    Act Density 0.003%

    No Known Activations