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

    Neuronpedia

    INDEX
    Explanations

    over a / by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.49
    統計
    0.42
    「
    0.42
    include
    0.40
     fiery
    0.40
     récit
    0.40
    Rasp
    0.40
    pinimg
    0.40
    理論
    0.40
    経
    0.39
    POSITIVE LOGITS
     mollus
    0.48
     مسی
    0.47
     earthquakes
    0.47
     Algeria
    0.47
     comenzamos
    0.46
    ່ມ
    0.46
     conoz
    0.45
     Emperors
    0.45
    ിൽ
    0.45
     Spaniards
    0.44
    Act Density 0.004%

    No Known Activations