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

    Neuronpedia

    INDEX
    Explanations

    daily schedules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     midnight
    0.84
    Midnight
    0.75
     nighttime
    0.73
     Midnight
    0.72
     nightly
    0.72
    midnight
    0.66
     tonight
    0.64
     bedtime
    0.62
     evening
    0.61
     apparently
    0.60
    POSITIVE LOGITS
    ígeno
    0.79
    imap
    0.77
     Sauber
    0.77
    自由に
    0.77
    celain
    0.76
     từ
    0.75
     부터
    0.74
    ophora
    0.73
     CALLBACK
    0.73
     പ്രദേശ
    0.73
    Act Density 0.037%

    No Known Activations