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

    Neuronpedia

    INDEX
    Explanations

    references to participants or involvement in activities or studies

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

    participating in groups or locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ródło
    -0.62
    ähteet
    -0.61
    rungsseite
    -0.60
    łość
    -0.60
     dieß
    -0.59
     препратки
    -0.58
     Sejarah
    -0.57
    ėjimas
    -0.57
     Gegenteil
    -0.57
     jagung
    -0.56
    POSITIVE LOGITS
     Participating
    1.02
    Participating
    0.99
     participating
    0.99
     Contributing
    0.82
     cooperating
    0.79
    Contributing
    0.78
     contributing
    0.77
     collaborating
    0.75
    operating
    0.71
     Coordinating
    0.71
    Act Density 0.042%

    No Known Activations