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

    Neuronpedia

    INDEX
    Explanations

    Emoji and foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Recht
    0.48
    angled
    0.48
    ianum
    0.48
     yanlı
    0.47
    unzione
    0.47
    峮
    0.47
     ljubav
    0.45
    anglement
    0.45
     견
    0.45
     คำ
    0.44
    POSITIVE LOGITS
    ك
    0.58
    ل
    0.55
    م
    0.45
    جور
    0.44
     You
    0.44
    私たち
    0.43
     टो
    0.42
    上に
    0.42
     ke
    0.42
    There
    0.42
    Act Density 0.001%

    No Known Activations