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

    Neuronpedia

    INDEX
    Explanations

    language and social structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一
    0.42
    對
    0.41
    رر
    0.39
    я
    0.39
    gladbach
    0.39
     Initially
    0.38
    比
    0.38
     запах
    0.38
    惠
    0.38
    ं
    0.38
    POSITIVE LOGITS
     language
    0.52
    Language
    0.50
    诗
    0.48
     viya
    0.47
     americanos
    0.46
     Traveller
    0.46
     texts
    0.45
     writings
    0.45
     язык
    0.45
     Language
    0.45
    Act Density 0.013%

    No Known Activations