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

    Neuronpedia

    INDEX
    Explanations

    Spanish pronouns and verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leitura
    0.98
     lettura
    0.97
     implementación
    0.96
     indiquant
    0.94
     คุณ
    0.90
     funzionamento
    0.89
     atualização
    0.88
     flusso
    0.88
     risposta
    0.88
     mohli
    0.87
    POSITIVE LOGITS
     se
    0.79
     le
    0.62
     lo
    0.60
     regrett
    0.56
     les
    0.55
     cause
    0.54
     no
    0.53
     gathers
    0.52
     era
    0.51
     arrives
    0.51
    Act Density 0.257%

    No Known Activations