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

    Neuronpedia

    INDEX
    Explanations

    Hummus, base lookup, like phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Guten
    0.50
     Fleurs
    0.47
    чин
    0.46
     Gens
    0.46
    чи
    0.45
    ⚠️
    0.44
     tắt
    0.44
    📉
    0.43
     Geme
    0.43
     Festive
    0.43
    POSITIVE LOGITS
    ú
    0.54
    og
    0.50
     revisited
    0.49
    ó
    0.48
     bids
    0.48
    कडील
    0.47
     wat
    0.47
    ří
    0.47
     incluindo
    0.47
    ያው
    0.47
    Act Density 0.000%

    No Known Activations