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

    Neuronpedia

    INDEX
    Explanations

    as the explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conceivably
    0.43
     educator
    0.40
     öğretmen
    0.40
     décrire
    0.40
     profesor
    0.40
    教师
    0.39
     kantor
    0.39
     लेक्चर
    0.39
     proteg
    0.39
     açıklam
    0.39
    POSITIVE LOGITS
     ингреди
    0.45
     elution
    0.45
     Racism
    0.43
    原始
    0.42
    でしたが
    0.42
     приносит
    0.42
    Przy
    0.41
    Importer
    0.41
    ಪೆ
    0.41
     Tasting
    0.40
    Act Density 0.029%

    No Known Activations