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

    Neuronpedia

    INDEX
    Explanations

    terms related to emotional expressions, specifically quotations and symbols that convey sentiments

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

    Preceding numbers or special characters

    np_acts-logits-general · gemini-2.0-flash

    Owen says

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нодоро
    -0.58
     _$
    -0.56
     temporales
    -0.56
    lapsingToolbar
    -0.56
     {})
    -0.55
    ANDUM
    -0.54
     erop
    -0.54
    titleMargin
    -0.54
     Latimer
    -0.53
    Décès
    -0.53
    POSITIVE LOGITS
    看你
    0.53
    例句
    0.52
    Obrázky
    0.51
     GenerationType
    0.49
     attending
    0.48
    MetaType
    0.48
     مشين
    0.47
    hibitions
    0.46
     lest
    0.45
    NOW
    0.45
    Act Density 0.113%

    No Known Activations