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

    Neuronpedia

    INDEX
    Explanations

    defense positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     globales
    0.87
    라
    0.86
    은
    0.84
    ܠܐ
    0.82
     Alexandra
    0.80
     vue
    0.80
    āda
    0.79
     Ada
    0.79
    }}}$
    0.79
    媺
    0.79
    POSITIVE LOGITS
    ру
    0.88
    mathrm
    0.76
    сного
    0.75
     department
    0.71
    department
    0.70
    লিখিত
    0.70
    ပိုင်း
    0.68
    tal
    0.67
     midfielder
    0.67
    sent
    0.66
    Act Density 0.023%

    No Known Activations