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

    Neuronpedia

    INDEX
    Explanations

    times of day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आई
    0.23
    美国
    0.21
    高兴
    0.20
    6
    0.20
    信息
    0.20
    我们
    0.19
    js
    0.19
    館
    0.19
    1
    0.19
     are
    0.19
    POSITIVE LOGITS
    ir
    0.26
     ABOUT
    0.23
     carbs
    0.22
    ου
    0.22
    sá
    0.21
     dusk
    0.21
    estad
    0.21
     JOB
    0.21
     시간이
    0.21
    ות
    0.20
    Act Density 0.112%

    No Known Activations