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

    Neuronpedia

    INDEX
    Explanations

    your request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propres
    0.37
     próprios
    0.34
     propias
    0.32
    自身の
    0.32
     propios
    0.32
     propio
    0.31
     próprias
    0.30
     own
    0.29
     própria
    0.29
     eigenen
    0.29
    POSITIVE LOGITS
     எனது
    0.31
     ನನ್ನ
    0.27
    example
    0.24
     मेरा
    0.23
     моя
    0.23
     என்னுடைய
    0.23
     मेरे
    0.23
     моего
    0.23
     minha
    0.22
     мой
    0.22
    Act Density 0.030%

    No Known Activations