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

    Neuronpedia

    INDEX
    Explanations

    re + [verb ending in -ing or -ed]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.54
     isang
    0.49
    és
    0.48
    uri
    0.46
    esh
    0.45
    스
    0.44
    𝗿
    0.44
     so
    0.44
    ine
    0.43
     l
    0.43
    POSITIVE LOGITS
    0.48
    นำ
    0.43
     gunakan
    0.42
     całość
    0.39
    nCurr
    0.39
    awarkan
    0.39
     overtake
    0.38
    ন
    0.38
    送到
    0.37
     kasutada
    0.37
    Act Density 1.117%

    No Known Activations