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

    Neuronpedia

    INDEX
    Explanations

    months and days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auk
    0.39
    abhavena
    0.39
    各位同學
    0.37
    わない
    0.36
    وة
    0.36
     efekt
    0.35
    Ple
    0.35
     fester
    0.33
     dressings
    0.32
     perin
    0.32
    POSITIVE LOGITS
     February
    0.67
     October
    0.63
     November
    0.61
     Saturday
    0.61
     Thursday
    0.61
     July
    0.60
     August
    0.60
     January
    0.57
     March
    0.55
     December
    0.55
    Act Density 0.001%

    No Known Activations