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

    Neuronpedia

    INDEX
    Explanations

    descriptive words and phrases that convey communication etiquette and social dynamics

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

    non-english or stylized text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.40
    ôtel
    -0.32
    TagHelper
    -0.31
     Mothers
    -0.31
     ter
    -0.31
     Veg
    -0.31
    ginald
    -0.31
     Ind
    -0.30
     onPause
    -0.30
    HtmlAttribute
    -0.29
    POSITIVE LOGITS
    arangay
    0.69
     كومونز
    0.66
    ſelf
    0.65
     increí
    0.64
    最快更新
    0.60
     indígen
    0.60
    alakip
    0.60
     laſſen
    0.59
     ſche
    0.58
    ementara
    0.57
    Act Density 0.121%

    No Known Activations