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

    Neuronpedia

    INDEX
    Explanations

    explaining or describing certain actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ба
    0.93
     устойчи
    0.90
    >
    0.90
     п
    0.88
     ﺍﻟ
    0.84
        
    0.81
     물
    0.81
     มาก
    0.80
     высоко
    0.80
     물질
    0.79
    POSITIVE LOGITS
     paragraph
    0.99
     suffice
    0.99
     passende
    0.97
     hearsay
    0.96
     lemmas
    0.94
     maksud
    0.91
     indicate
    0.91
     accessori
    0.89
     entsprechende
    0.88
     ditulis
    0.88
    Act Density 7.361%

    No Known Activations