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

    Neuronpedia

    INDEX
    Explanations

    specific references to measurements, dates, and scientific data points

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

    measurement units or plural nouns

    np_acts-logits-general · gemini-2.0-flash

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.79
     gawas
    -0.73
     Infatti
    -0.69
    simpleType
    -0.69
     FetchType
    -0.69
    مراجع
    -0.68
    __':
    -0.67
    anskje
    -0.67
     Seeder
    -0.67
    ThroughAttribute
    -0.64
    POSITIVE LOGITS
     entrambi
    0.93
     respectively
    0.90
    both
    0.88
    どちらも
    0.83
     ambos
    0.83
     respectivamente
    0.82
     both
    0.82
     beide
    0.81
    Both
    0.80
     Both
    0.80
    Act Density 0.767%

    No Known Activations