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

    Neuronpedia

    INDEX
    Explanations

    technical identifiers, likely related to programming or code elements

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embreagem
    -0.45
     indefinitely
    -0.45
     nationally
    -0.43
     ģ
    -0.41
     gjø
    -0.40
     historically
    -0.40
     tarjeta
    -0.40
    ジェクト
    -0.39
     vícti
    -0.39
     borracha
    -0.39
    POSITIVE LOGITS
    parsedMessage
    0.92
    Personensuche
    0.75
    AddTagHelper
    0.71
     незавершена
    0.70
    tagHelperRunner
    0.69
     protoimpl
    0.69
    хьтан
    0.65
    OGND
    0.65
     Numerade
    0.62
     estekak
    0.62
    Act Density 0.003%

    No Known Activations