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

    Neuronpedia

    INDEX
    Explanations

    nav menu HTML structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    0.90
     файлов
    0.82
    пы
    0.73
    o
    0.71
    ਰ
    0.71
    ология
    0.71
     newfound
    0.70
    вер
    0.69
    蟀
    0.68
    дается
    0.67
    POSITIVE LOGITS
     Oncology
    0.89
     cambiare
    0.83
     aumentare
    0.81
     істори
    0.80
    gress
    0.80
     ieri
    0.79
     Figures
    0.78
     entraî
    0.77
    ?.
    0.76
     ora
    0.75
    Act Density 0.001%

    No Known Activations