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

    Neuronpedia

    INDEX
    Explanations

    times of day and meals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     стрем
    0.37
     você
    0.35
     شما
    0.33
    heel
    0.33
     identify
    0.32
    岂
    0.32
     sqrt
    0.32
     ≤
    0.32
     aligns
    0.31
     belief
    0.31
    POSITIVE LOGITS
     вечер
    0.46
     lunches
    0.43
     diner
    0.41
    晚餐
    0.41
     Frühstück
    0.40
     bathrobe
    0.40
     lunch
    0.39
     breakfasts
    0.39
     morning
    0.39
     evening
    0.39
    Act Density 0.121%

    No Known Activations