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

    Neuronpedia

    INDEX
    Explanations

    and other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lty
    1.19
    lor
    1.12
    rology
    1.03
     reparation
    1.01
    iz
    0.98
    shp
    0.96
    cun
    0.96
    uot
    0.95
    wiches
    0.95
    nment
    0.95
    POSITIVE LOGITS
     Çünkü
    1.46
    この
    1.38
     この
    1.38
     gunakan
    1.38
     questão
    1.34
     Tämä
    1.34
     этому
    1.31
    इन
    1.28
     будет
    1.28
     Enquanto
    1.27
    Act Density 0.261%

    No Known Activations