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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    np_acts-logits-general · gemini-2.5-flash-lite

    days and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.79
    ן
    0.75
    ล
    0.74
    ai
    0.66
    ל
    0.65
    TP
    0.64
    ו
    0.63
    د
    0.63
    ল
    0.63
    )
    0.62
    POSITIVE LOGITS
    f
    0.93
    ра
    0.89
    h
    0.84
    ве
    0.80
    c
    0.79
    morning
    0.75
     categor
    0.75
     ಇಂದು
    0.74
     शुक्रवार
    0.72
    ал
    0.70
    Act Density 0.875%

    No Known Activations