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

    Neuronpedia

    INDEX
    Explanations

    sensing others' feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.32
    สร้าง
    0.30
     twor
    0.28
    }
    0.26
    将
    0.26
     slicing
    0.25
     delimiters
    0.25
     polygons
    0.25
    m
    0.25
    קי
    0.24
    POSITIVE LOGITS
    感受到
    0.39
     комфор
    0.33
    情绪
    0.32
     Feels
    0.32
     sentirse
    0.31
     desiderio
    0.31
     чувства
    0.31
     confortable
    0.30
     желание
    0.30
    чув
    0.29
    Act Density 1.962%

    No Known Activations