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

    Neuronpedia

    INDEX
    Explanations

    themes related to human experiences and emotions

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

    abilities, origins, or advantages

    np_acts-logits-general · gemini-2.0-flash

    acquired abilities and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.65
     történ
    -0.63
    migrationBuilder
    -0.61
    Наводи
    -0.60
    ArrowToggle
    -0.55
    uitton
    -0.53
    expandindo
    -0.51
    monix
    -0.50
    robe
    -0.50
     الرخصة
    -0.48
    POSITIVE LOGITS
     adquirido
    0.65
     conferred
    0.64
     dimiliki
    0.64
     gained
    0.63
     advantage
    0.61
     متعلقه
    0.60
     acquired
    0.58
    blem
    0.58
     bestowed
    0.56
     invokingState
    0.56
    Act Density 0.472%

    No Known Activations