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

    Neuronpedia

    INDEX
    Explanations

    months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    जिस
    0.56
    О
    0.51
    ratio
    0.48
    capable
    0.47
    http
    0.47
    И
    0.46
    ogl
    0.46
    not
    0.46
    )$;
    0.46
    subset
    0.45
    POSITIVE LOGITS
     Madness
    0.83
     Month
    0.71
     মাসে
    0.69
    下旬
    0.68
     меся
    0.68
     месяца
    0.68
     September
    0.66
     ۱۵
    0.66
     ۲۰
    0.66
     month
    0.66
    Act Density 0.022%

    No Known Activations