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

    Neuronpedia

    INDEX
    Explanations

    references to food, dining experiences, and social interactions related to meals

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

    generation comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.57
    invokeLater
    -0.55
     Савезне
    -0.55
    complexType
    -0.52
     autorytatywna
    -0.50
     للاسماء
    -0.50
     ویکی‌پدی
    -0.49
    TypedDataSet
    -0.48
    PreInfinity
    -0.47
    IUrlHelper
    -0.47
    POSITIVE LOGITS
     tet
    0.41
    caud
    0.39
    🏻
    0.38
    Tet
    0.36
    melon
    0.35
     Tet
    0.35
    modern
    0.35
    AFN
    0.34
     Aux
    0.34
     harmony
    0.33
    Act Density 0.107%

    No Known Activations