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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases related to emotions and abstract concepts

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

    天香 or 绝情

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inval
    -0.31
     whatever
    -0.30
     mentales
    -0.29
     ſt
    -0.28
    Kontrola
    -0.28
    postIndex
    -0.28
    %)$
    -0.27
    jadi
    -0.27
     noe
    -0.27
    Über
    -0.27
    POSITIVE LOGITS
    Diweddarwch
    0.75
     ExecuteAsync
    0.65
    Personendaten
    0.59
     صوتيه
    0.59
    ArrowToggle
    0.57
     AssemblyCompany
    0.57
    ViewFeatures
    0.54
     насељу
    0.54
     Wikimedijinoj
    0.52
     Савезне
    0.52
    Act Density 0.023%

    No Known Activations