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

    Neuronpedia

    INDEX
    Explanations

    un/una/une/um

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    are
    0.45
    an
    0.45
     aynı
    0.42
     stesso
    0.38
    ↵↵
    0.37
    along
    0.36
    trimenti
    0.36
    it
    0.36
    they
    0.35
     it
    0.35
    POSITIVE LOGITS
     situación
    0.39
    ث
    0.39
    ق
    0.38
    ت
    0.37
     vajj
    0.37
    ס
    0.37
    Ⴀ
    0.36
     manifestaciones
    0.36
     referencias
    0.36
     situaciones
    0.36
    Act Density 0.172%

    No Known Activations