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

    Neuronpedia

    INDEX
    Explanations

    words and phrases in other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     famously
    0.54
     Anybody
    0.52
    popularity
    0.52
    CAR
    0.51
    Memor
    0.50
    Revolution
    0.50
    findOne
    0.49
     damals
    0.49
     roky
    0.49
     defunct
    0.49
    POSITIVE LOGITS
     которые
    0.74
    仍然
    0.64
     نئے
    0.62
     amelyek
    0.61
    ované
    0.61
     новых
    0.60
    ometric
    0.60
     якія
    0.60
     новые
    0.59
     które
    0.58
    Act Density 0.000%

    No Known Activations