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

    Neuronpedia

    INDEX
    Explanations

    current date in November

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     März
    0.81
     spring
    0.78
     March
    0.77
     April
    0.76
     yat
    0.76
     april
    0.75
     marzo
    0.74
     september
    0.73
    March
    0.73
    Dates
    0.72
    POSITIVE LOGITS
     माहिती
    0.65
    abble
    0.62
    abha
    0.60
    WithDictionary
    0.59
    辑
    0.58
     জানিয়ে
    0.57
     Ott
    0.57
    abee
    0.57
    নো
    0.56
    getPackageName
    0.56
    Act Density 0.019%

    No Known Activations