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

    Neuronpedia

    INDEX
    Explanations

    long short-term memory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dài
    0.55
     طول
    0.54
     dłu
    0.52
     लंबा
    0.51
     læng
    0.48
     längre
    0.48
    長い
    0.47
     lengthened
    0.47
     panjang
    0.47
     lenght
    0.46
    POSITIVE LOGITS
    itude
    0.42
    Bailey
    0.38
    zhang
    0.37
     MA
    0.35
    chae
    0.35
     harder
    0.35
    i
    0.34
    itudinal
    0.34
    nm
    0.34
     terminology
    0.33
    Act Density 0.014%

    No Known Activations