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

    Neuronpedia

    INDEX
    Explanations

    connecting certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mile
    0.45
    ↵
    0.42
    ters
    0.41
     belg
    0.41
    شمند
    0.41
    rola
    0.41
     mile
    0.40
     hein
    0.40
     roar
    0.40
    ot
    0.38
    POSITIVE LOGITS
     연결
    0.53
     식
    0.52
    ૯
    0.49
    Ẫ
    0.47
    POD
    0.46
    ဝ
    0.45
    不说
    0.45
    যোগ
    0.45
     이미지
    0.44
    洗衣
    0.44
    Act Density 0.001%

    No Known Activations