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

    Neuronpedia

    INDEX
    Explanations

    Valentine's Day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.53
    q
    0.53
    l
    0.48
    ল
    0.48
    ل
    0.47
    er
    0.46
    o
    0.46
     earnest
    0.45
     bent
    0.43
    D
    0.43
    POSITIVE LOGITS
    袭击
    0.48
     HUB
    0.47
     শাব
    0.46
    धिकारिक
    0.46
     উচিৎ
    0.46
    ध्ये
    0.45
     नक
    0.45
     obecnie
    0.45
    咂
    0.44
     Clín
    0.44
    Act Density 0.002%

    No Known Activations