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

    Neuronpedia

    INDEX
    Explanations

    results and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essentials
    0.77
     বিপদ
    0.75
     lest
    0.74
    ालत
    0.71
     menace
    0.71
    する必要
    0.71
    purpose
    0.71
     submission
    0.69
     Lending
    0.68
     प्रोटे
    0.68
    POSITIVE LOGITS
    จากการ
    1.14
     esperado
    1.04
     obtenidos
    1.03
     obtenido
    1.02
     measurable
    0.99
     esperaba
    0.99
     rezultat
    0.97
     resultados
    0.96
     resultado
    0.95
     résultat
    0.94
    Act Density 0.428%

    No Known Activations