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

    Neuronpedia

    INDEX
    Explanations

    in deep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     populer
    0.42
     wifi
    0.41
     privé
    0.40
     wanita
    0.40
     znaleźć
    0.39
     की
    0.39
     ratus
    0.39
     sof
    0.38
     dvd
    0.38
     menampilkan
    0.38
    POSITIVE LOGITS
    Nationality
    0.49
    работки
    0.44
    Newswire
    0.42
    Means
    0.41
    Below
    0.41
    Placed
    0.41
    Not
    0.40
    Must
    0.40
    разу
    0.40
    Localization
    0.40
    Act Density 0.000%

    No Known Activations