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

    Neuronpedia

    INDEX
    Explanations

    codes and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    碖
    0.43
    Polygon
    0.42
    amn
    0.42
     lemma
    0.42
     pronotum
    0.42
    答
    0.41
    所述
    0.39
     sizin
    0.39
    😿
    0.39
     فيه
    0.39
    POSITIVE LOGITS
     hợp
    0.49
     EDUCATION
    0.44
    Т
    0.43
     ngày
    0.42
     educação
    0.42
     educación
    0.41
    ବ
    0.41
     modernes
    0.41
    EDUCATION
    0.40
     एजुकेशन
    0.40
    Act Density 0.000%

    No Known Activations