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

    Neuronpedia

    INDEX
    Explanations

    disambiguating multiple meanings in context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     подчер
    0.46
     podkre
    0.43
     emphasized
    0.43
     процессе
    0.43
     sottoline
    0.42
     vorher
    0.40
     ideally
    0.39
    нед
    0.39
    理想
    0.39
     emphasised
    0.38
    POSITIVE LOGITS
     meanings
    0.79
     disamb
    0.75
    disamb
    0.71
    Meaning
    0.66
    含义
    0.63
     meaning
    0.63
     contexts
    0.61
     significato
    0.61
     Meaning
    0.60
     refers
    0.59
    Act Density 0.021%

    No Known Activations