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

    Neuronpedia

    INDEX
    Explanations

    other [category]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    时间和
    0.46
     both
    0.46
     zarówno
    0.43
     både
    0.42
    Both
    0.38
     BOTH
    0.37
     (“
    0.37
     zowel
    0.37
     tides
    0.36
     başta
    0.36
    POSITIVE LOGITS
     подобные
    0.68
     whatnot
    0.61
     assorted
    0.58
     similares
    0.58
     অন্যান্য
    0.56
     ఇతర
    0.56
     подобных
    0.55
     paraphernalia
    0.54
     अन्य
    0.54
     sundry
    0.53
    Act Density 0.020%

    No Known Activations