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

    Neuronpedia

    INDEX
    Explanations

    사랑해요, 귀여워

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Расійскай
    1.67
     uninterrupted
    1.60
     packaged
    1.59
     relaxed
    1.55
     nourishing
    1.54
     revered
    1.54
     choked
    1.54
     disrupted
    1.51
     looming
    1.50
     secluded
    1.50
    POSITIVE LOGITS
    기
    2.58
     기
    2.53
    자
    2.51
    가
    2.48
     수
    2.44
     세
    2.43
     가
    2.42
     고
    2.42
     소
    2.39
     재
    2.38
    Act Density 0.011%

    No Known Activations