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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons and trends in data

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

    describing qualities or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Дереккөздер
    -0.52
    клопе
    -0.48
    historie
    -0.42
    laughing
    -0.42
     Dom
    -0.41
     Dove
    -0.41
    parrot
    -0.41
     Jam
    -0.41
    niño
    -0.40
    assumption
    -0.40
    POSITIVE LOGITS
    ########.
    0.47
    0.41
    ScopeManager
    0.39
     AssemblyCompany
    0.38
     oprot
    0.38
    Попис
    0.38
     finestra
    0.38
     Biôgrafia
    0.35
    sizeCache
    0.35
    DoubleQuotes
    0.35
    Act Density 0.184%

    No Known Activations