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

    Neuronpedia

    INDEX
    Explanations

    programming keywords and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    喟
    0.42
     Frage
    0.41
    견
    0.41
    らっしゃる
    0.40
     gevoel
    0.39
    حية
    0.39
    رس
    0.39
    ネイル
    0.39
    एर
    0.39
     Publisher
    0.38
    POSITIVE LOGITS
    y
    0.49
    in
    0.44
     до
    0.43
    ón
    0.43
    ett
    0.43
    n
    0.43
    elly
    0.42
    ct
    0.42
    ilium
    0.41
     отсутствует
    0.41
    Act Density 0.001%

    No Known Activations