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

    Neuronpedia

    INDEX
    Explanations

    code and foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人の
    0.19
    া
    0.19
    われます
    0.18
    ેશ
    0.18
    0.18
    人を
    0.18
    ρίας
    0.18
     determining
    0.17
    жды
    0.17
     attainment
    0.17
    POSITIVE LOGITS
     neuer
    0.23
     mlij
    0.21
     knj
    0.20
     serupa
    0.19
     ikke
    0.18
     nicht
    0.18
     bril
    0.18
     vuelva
    0.18
     contrario
    0.18
     drugi
    0.18
    Act Density 0.585%

    No Known Activations