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

    Neuronpedia

    INDEX
    Explanations

    sentiments of approval or disapproval related to decisions and social policies

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

    Following opinions or actions

    np_acts-logits-general · gemini-2.0-flash

    strongly opposed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.64
    stdafx
    -0.63
    tagHelperRunner
    -0.60
    abestanden
    -0.55
     člověk
    -0.54
    Ligações
    -0.54
    پیوند
    -0.52
    '])){
    -0.52
    StoryboardSegue
    -0.52
     człowiek
    -0.51
    POSITIVE LOGITS
     attract
    0.74
     attracting
    0.71
     favored
    0.63
     according
    0.62
    引起了
    0.61
     attracts
    0.59
     piaci
    0.57
     لدى
    0.57
     مورد
    0.57
    httphttps
    0.56
    Act Density 0.396%

    No Known Activations