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

    Neuronpedia

    INDEX
    Explanations

    idiomas e capacidade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fauna
    1.07
     Cadastro
    1.02
     inox
    1.00
     българ
    1.00
     Chic
    0.97
     Milit
    0.92
     Entities
    0.91
     poter
    0.89
     Porém
    0.89
     cadastro
    0.89
    POSITIVE LOGITS
     potencialmente
    0.96
     möglicherweise
    0.92
     einschließlich
    0.88
     cuidadosamente
    0.87
    ientemente
    0.84
     todavía
    0.82
     keterampilan
    0.79
     tetapi
    0.78
     probablemente
    0.77
     realmente
    0.76
    Act Density 0.434%

    No Known Activations