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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and physical interactions

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

    welcoming guests to places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.82
    IBOutlet
    -0.67
     autorytatywna
    -0.65
    sizeCache
    -0.63
    +#+#
    -0.62
     للمعارف
    -0.59
    TypedDataSet
    -0.59
     NSCoder
    -0.58
     IBOutlet
    -0.53
    BeginContext
    -0.52
    POSITIVE LOGITS
     accueille
    0.48
     welcoming
    0.47
     welcomes
    0.46
     accue
    0.44
     receber
    0.42
     guest
    0.40
     accueillir
    0.40
    guest
    0.40
     god
    0.40
     home
    0.39
    Act Density 0.162%

    No Known Activations