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

    Neuronpedia

    INDEX
    Explanations

    months and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     October
    0.62
     Autumn
    0.62
     February
    0.57
    <unused730>
    0.55
     November
    0.52
     Prevention
    0.51
    ރ
    0.51
     Wein
    0.51
     Ağustos
    0.50
    <unused416>
    0.50
    POSITIVE LOGITS
    BE
    0.47
    CHA
    0.46
    F
    0.45
    Energie
    0.45
    FORT
    0.42
    Altri
    0.41
    PE
    0.41
    PCs
    0.40
     zwei
    0.40
     be
    0.40
    Act Density 0.013%

    No Known Activations