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

    Neuronpedia

    INDEX
    Explanations

    the presence of conjunctions and phrases indicating relationships within the text

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

    "and" followed by a type of descriptor

    np_acts-logits-general · gemini-2.0-flash

    and linking related aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Protestantism
    -0.70
     osmosis
    -0.69
    PreferredItem
    -0.68
    endphp
    -0.63
    fortawesome
    -0.62
     protoimpl
    -0.62
    MockBean
    -0.62
    例文
    -0.62
     comets
    -0.61
     loob
    -0.61
    POSITIVE LOGITS
    }:${
    0.52
     illetve
    0.49
    '])->
    0.48
    }">
    0.47
    aarrggbb
    0.46
    atial
    0.46
    orological
    0.45
     puis
    0.45
    Див
    0.45
     non
    0.45
    Act Density 0.630%

    No Known Activations