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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and prepositions related to location or direction

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

    "In" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    in which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aholisi
    -0.60
    ází
    -0.55
    цезда
    -0.54
    ádza
    -0.49
    trás
    -0.48
    figer
    -0.47
    ConverterFactory
    -0.47
     között
    -0.45
     feveral
    -0.45
     архивлан
    -0.45
    POSITIVE LOGITS
     which
    1.05
     WHICH
    0.87
    which
    0.86
     cui
    0.76
     Which
    0.73
    Which
    0.69
    tagHelperRunner
    0.67
     فريبيس
    0.65
     }}"></
    0.64
     Мексичка
    0.63
    Act Density 0.540%

    No Known Activations